2
A
B
C
D
E
F
H
I
J
L
M
N
P
R
S
T
V
W

Keywords from titles, sorted alphabetically. Click any keyword to read the post.

#
ML Frontier #01: Neural Collapse
ML Frontier #02: In-Context Reinforcement Learning
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
ML Frontier #04: Is Chain of Thought Real?
ML Frontier #05: Grokking --- Delayed Generalization
Five ML Concepts - #21
Five ML Concepts - #22
Five ML Concepts - #23
Five ML Concepts - #24
Five ML Concepts - #25
Five ML Concepts - #26
Five ML Concepts - #27
Five ML Concepts - #28
Five ML Concepts - #29
Five ML Concepts - #30: The Journey So Far
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ #osdev IRC
'
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
(
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ (B) '75
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ (B) '75
1
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ 1.58-bit ternary network
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ 16-bit
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ 1965
TBT #1: My First Program Was a Horse Race ~ 1972
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
TBT #2: Pipelines on OS/390 ~ 1996 Olympics
2
Lucy 20%: Upgrading My Home AI Cluster
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ 2048
Lucy 20%: Upgrading My Home AI Cluster ~ 24GB VRAM
Saw #11: Building a Tiny Mixture of Experts Microscope ~ 256 MB
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
Small Models (3/6): Planner + Doer = Genius ~ 27M parameters
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ 2-round XMX
3
Five ML Concepts - #1 ~ 30-second explainers
Five ML Concepts - #21 ~ 30-second explainers
Five ML Concepts - #22 ~ 30-second explainers
Five ML Concepts - #23 ~ 30-second explainers
Five ML Concepts - #24 ~ 30-second explainers
Five ML Concepts - #25 ~ 30-second explainers
Five ML Concepts - #26 ~ 30-second explainers
Five ML Concepts - #27 ~ 30-second explainers
Five ML Concepts - #28 ~ 30-second explainers
Five ML Concepts - #29 ~ 30-second explainers
Five ML Concepts - #2 ~ 30-second explainers
Five ML Concepts - #30: The Journey So Far ~ 30-second explainers
Five ML Concepts - #3 ~ 30-second explainers
Five ML Concepts - #4 ~ 30-second explainers
Five ML Concepts - #5 ~ 30-second explainers
Five ML Concepts - #6 ~ 30-second explainers
Five ML Concepts - #7 ~ 30-second explainers
Five ML Concepts - #8 ~ 30-second explainers
Five ML Concepts - #9 ~ 30-second explainers
Five ML Concepts - #10 ~ 30-second explainers
Five ML Concepts - #11 ~ 30-second explainers
Five ML Concepts - #12 ~ 30-second explainers
Five ML Concepts - #13 ~ 30-second explainers
Five ML Concepts - #14 ~ 30-second explainers
Five ML Concepts - #15 ~ 30-second explainers
Five ML Concepts - #16 ~ 30-second explainers
Five ML Concepts - #17 ~ 30-second explainers
Five ML Concepts - #18 ~ 30-second explainers
Five ML Concepts - #19 ~ 30-second explainers
Five ML Concepts - #20 ~ 30-second explainers
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ 3270
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ 32-bit MCU
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ 3Blue1Brown Essence of Linear Algebra
Made Visible #1: A Microkernel's Storage, Drawn ~ 3D memory map
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ 3D scene generation
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ 3D scene
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ 3D source code
4
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ 4-bit machine
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ 4K static RAM board price
5
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
6
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
7
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
9
Small Models (1/6): 976 Parameters Beat Billions ~ 976 parameters
Small Models (1/6): 976 Parameters Beat Billions
A
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ A* search
Five ML Concepts - #16 ~ A/B testing
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ abelian sandpile
Saw #12: A Model That Decides, and an Index That Knows ~ abstention
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ abstract algebra
Small Models (3/6): Planner + Doer = Genius ~ abstract reasoning
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ accelerator IR
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ accidental complexity
rank-wav: Ranking Audio Files by Acoustic Quality ~ acoustic features
rank-wav: Ranking Audio Files by Acoustic Quality
AI Tools #7: A Coding Agent Small Enough to Understand ~ action protocol
Five ML Concepts - #4 ~ activation functions
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Ada Lovelace
Five ML Concepts - #4 ~ Adam optimizer
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ Adam
How AI Learns Part 6: Toward Continuous Learning ~ adapter evolution
How AI Learns Part 1: The Many Meanings of Learning ~ adapters
How AI Learns Part 3: Weight-Based Learning ~ adapters
ML Frontier #04: Is Chain of Thought Real? ~ adaptive reasoning
Personal Software #10: A Sudoku That Teaches You the Strategies ~ ad-free
TBT #11: APL\360 Revisited ~ Adin Falkoff
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
Five ML Concepts - #25 ~ adversarial attacks
Five ML Concepts - #25 ~ adversarial examples
Rabbit-hole #3: FORTH --- Life After Hashing
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ agent coordination
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ agent isolation
AI Tools #7: A Coding Agent Small Enough to Understand ~ agent loop
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ agent memory
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ agent workflow
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ agentic coding
Bucket List #2: A Landing Page for Software Tools ~ agentrail-rs
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ agentrail-rs
Saw #2: reg-rs, avoid-compaction, and agentrail-rs
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Saw #5: Sagas, Languages, and Compiler Chains ~ agentrail-rs
Saw #15: agentrail, Correcting the Record ~ agentrail-rs
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ AgentRail
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ agentrail
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ AgentRail
Personal Software #10: A Sudoku That Teaches You the Strategies ~ AgentRail
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ agentrail
Saw #15: agentrail, Correcting the Record ~ agentrail
Saw #15: agentrail, Correcting the Record
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
midi-cli-rs: Music Generation for AI Coding Agents
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
AI Tools #7: A Coding Agent Small Enough to Understand
How AI Learns Part 7: Designing a Continuous Learning Agent
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
How AI Learns Part 7: Designing a Continuous Learning Agent ~ AI agent architecture
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ AI agent security
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ AI agents
ML Frontier #02: In-Context Reinforcement Learning ~ AI agents
ML Frontier #04: Is Chain of Thought Real? ~ AI agents
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ AI agents
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ AI agents
midi-cli-rs: Music Generation for AI Coding Agents ~ AI agents
Five ML Concepts - #26 ~ AI alignment
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ AI bug fixing
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ AI coding agents
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ AI coding agents
Bucket List #1: Things I've Always Wanted to Build ~ AI coding agents
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ AI coding agents
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ AI coding agents
Saw #15: agentrail, Correcting the Record ~ AI coding agents
Lucy 20%: Upgrading My Home AI Cluster ~ AI hardware
How AI Learns Part 1: The Many Meanings of Learning ~ AI memory
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ AI test generation
Five ML Concepts - #23 ~ AI tool calling
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ AI Tools
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
music-pipe-rs: Unix Pipelines for MIDI Composition ~ algorithmic composition
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ algorithmic composition
ML Frontier #05: Grokking --- Delayed Generalization ~ algorithmic datasets
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ algorithmic-bloat
Five ML Concepts - #24 ~ alignment
Five ML Concepts - #30: The Journey So Far ~ alignment
How AI Learns Part 3: Weight-Based Learning ~ alignment
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ all-together-now
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Bucket List #1: Things I've Always Wanted to Build
midi-cli-rs: Music Generation for AI Coding Agents ~ ambient
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Ampere
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Apicula
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ APL course
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ APL execute
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ APL glyphs
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ APL train
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ APL without an APL keyboard
Array Languages #1: X_eTaL, an Array Language You Can Read ~ APL without glyphs
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ apl2 idioms
Made Visible #4: Rosetta M, a Stone with Four Faces ~ APL2
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ APL2
TBT #11: APL\360 Revisited ~ APL2
TBT #11: APL\360 Revisited ~ APL\360
TBT #11: APL\360 Revisited
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ APLSV
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ APLSV
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Machine Learning #9: Teaching an Array Language to Say CNN ~ APL
Saw #5: Sagas, Languages, and Compiler Chains ~ APL
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ APL
TBT #11: APL\360 Revisited ~ APL
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ APL
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ APL
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Apple M1 Max
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Apple M3 Pro
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ AQ system
Small Models (3/6): Planner + Doer = Genius ~ ARC challenge
TBT #3: Vector Graphics Games ~ arcade games
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ Arch Linux
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ archive
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Arduino SRAM
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ Arduino UNO Q GPU
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ arm64
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ ARM64
music-pipe-rs: Web Demo and Multi-Instrument Arrangements
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ array language 3D graphics
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ array language GPU
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ array language idioms
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ array language libraries
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ array language on GPU through Mojo
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ array language on GPU
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ array language to hardware
Array Languages #14: Types, Lints and Errors in X_eTaL ~ array language type inference
Array Languages #1: X_eTaL, an Array Language You Can Read ~ array language
Machine Learning #9: Teaching an Array Language to Say CNN ~ array language
Made Visible #4: Rosetta M, a Stone with Four Faces ~ array language
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ array language
TBT #11: APL\360 Revisited ~ array language
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ array programming demos
Made Visible #1: A Microkernel's Storage, Drawn ~ array programming
TBT #1: My First Program Was a Horse Race ~ array programming
Array Languages #6: X_eTaL-games, Rules That Are Arrays
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Array Languages #1: X_eTaL, an Array Language You Can Read
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
Machine Learning #9: Teaching an Array Language to Say CNN
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Array Languages #11: Math Equations as X_eTaL Macros
Array Languages #12: ML Pipelines as X_eTaL Macros
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
Array Languages #14: Types, Lints and Errors in X_eTaL
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Array Languages #17: What Makes a Practical Language, IMHO
Array Languages #1: X_eTaL, an Array Language You Can Read
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Array Languages #4: X_eTaL-extensions, Extending the Machine
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
Array Languages #6: X_eTaL-games, Rules That Are Arrays
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Array Languages #1: X_eTaL, an Array Language You Can Read ~ ASCII APL
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ ASCII source rendered notation
JSON et al: A Deep Dive into Data Serialization Formats ~ ASN.1
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ assembly language
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ assembly language
Embedded #2: COR24-RS --- Learn Assembly in Your Browser
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ assembly
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ AST viewer
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ asteroids
TBT #3: Vector Graphics Games ~ Asteroids
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Atomic Pi
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot ~ attention dilution
Five ML Concepts - #2 ~ attention mechanism
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ attention microscope
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ attention
Five ML Concepts - #14 ~ AUC
rank-wav: Ranking Audio Files by Acoustic Quality ~ audio ranking
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ audio synthesizer
midi-cli-rs: Extending with Custom Mood Packs ~ audio
midi-cli-rs: Music Generation for AI Coding Agents ~ audio
music-pipe-rs: Unix Pipelines for MIDI Composition ~ audio
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ audio
rank-wav: Ranking Audio Files by Acoustic Quality
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ audit
Five ML Concepts - #19 ~ autoencoders
Machine Learning #9: Teaching an Array Language to Say CNN ~ autograd
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ autograd
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ avoid-compaction
Saw #2: reg-rs, avoid-compaction, and agentrail-rs
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ avoxelgame
JSON et al: A Deep Dive into Data Serialization Formats ~ Avro
Machine Learning #9: Teaching an Array Language to Say CNN ~ axis labels
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ Axum
B
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ B M L
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ B75
Small Models (4/6): This AI Has a Visible Brain ~ Baby Dragon Hatchling
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ Bach
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ backpropagation
Five ML Concepts - #1 ~ backpropagation
Five ML Concepts - #30: The Journey So Far ~ backpropagation
Neural-Net-RS: An Educational Neural Network Platform ~ backpropagation
Personal Software #10: A Sudoku That Teaches You the Strategies ~ backtracking solver
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ barometric pressure
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ Baroque
Saw #5: Sagas, Languages, and Compiler Chains ~ BASIC interpreter
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ BASIC
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ batch compile job
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ batch job submission
Five ML Concepts - #16 ~ batch normalization
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ batch queue
Five ML Concepts - #12 ~ batch size
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ batched matrix product
TBT #3: Vector Graphics Games ~ BattleZone
Small Models (4/6): This AI Has a Visible Brain ~ BDH
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Small Models (1/6): 976 Parameters Beat Billions
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ before Emacs
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ before IDEs
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Five ML Concepts - #17 ~ benchmark leakage
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
Five ML Concepts - #6 ~ BERT
Five ML Concepts - #8 ~ bias-variance tradeoff
Five ML Concepts - #6 ~ bidirectional encoder
Small Models (1/6): 976 Parameters Beat Billions
JSON et al: A Deep Dive into Data Serialization Formats ~ binary formats
Large-Language-Monkeys: Scaling Inference, Not Models ~ binary search
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ binary testing
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ binding macro
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ BIRDS
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ bit-banged GPIO emulation
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Blackwell
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ Blender animation of convolution
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ Blender batch rendering
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ Blender extension
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Bucket List #1: Things I've Always Wanted to Build ~ Blender
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
Made Visible #1: A Microkernel's Storage, Drawn ~ block map
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ blog validation
Welcome to Software Wrighter Lab ~ blog
Five ML Concepts - #24 ~ blue/green deployment
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ bluebird
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ BMP280
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ BMP581
Energy-Based Learning: From Hopfield Networks to JEPA ~ Boltzmann machine
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ bootstrap words
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ bootstrapping compiler
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ bootstrapping
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ box function convolution
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ bpy code generation
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ bpy
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ BQN bqn-libs
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ BQN
TBT #11: APL\360 Revisited ~ BQN
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Small Models (4/6): This AI Has a Visible Brain
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
Large-Language-Monkeys: Scaling Inference, Not Models ~ Brown 2024
Saw #12: A Model That Decides, and an Index That Knows ~ browser demo
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ browser storage
Embedded #2: COR24-RS --- Learn Assembly in Your Browser
Bucket List #1: Things I've Always Wanted to Build ~ bucket list
Bucket List #2: A Landing Page for Software Tools ~ bucket list
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ bucket list
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ bucket list
Bucket List #1: Things I've Always Wanted to Build
Bucket List #2: A Landing Page for Software Tools
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Saw #11: Building a Tiny Mixture of Experts Microscope
Bucket List #1: Things I've Always Wanted to Build
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ bump allocator
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
C
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ C ABI descriptor
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ C ABI
Saw #5: Sagas, Languages, and Compiler Chains ~ C compiler
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ cache key
How AI Learns Part 4: Memory-Based Learning ~ Cache-Augmented Generation
Five ML Concepts - #26 ~ caching strategies
How AI Learns Part 4: Memory-Based Learning ~ CAG
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ calculator
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ calibration
Five ML Concepts - #13 ~ calibration
Saw #12: A Model That Decides, and an Index That Knows ~ calibration
Made Visible #4: Rosetta M, a Stone with Four Faces ~ callouts
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ camera orbit animation
Saw #11: Building a Tiny Mixture of Experts Microscope ~ Campus Docent
Personal Software #11: A Campus for the Public Work
Five ML Concepts - #23 ~ canary deployment
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ Candle
AI Tools #7: A Coding Agent Small Enough to Understand ~ capability ledger
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ capacity-limit bumps
Personal Software #10: A Sudoku That Teaches You the Strategies ~ cargo workspace
Cat Finder: Personal Software via Vibe Coding ~ cat finder
Saw #11: Building a Tiny Mixture of Experts Microscope ~ catalog versus weights
Five ML Concepts - #27 ~ catastrophic forgetting
Five ML Concepts - #15 ~ catastrophic forgetting
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot ~ catastrophic forgetting
ML Frontier #01: Neural Collapse ~ catastrophic forgetting
Saw #11: Building a Tiny Mixture of Experts Microscope ~ catastrophic forgetting
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ catastrophic forgetting
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ catastrophic forgetting
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ category theory
Cat Finder: Personal Software via Vibe Coding
JSON et al: A Deep Dive into Data Serialization Formats ~ CBOR
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ cdylib
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ cellular automata
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ cellular automaton
Five ML Concepts - #11 ~ chain of thought
ML Frontier #04: Is Chain of Thought Real? ~ chain of thought
Saw #5: Sagas, Languages, and Compiler Chains
ML Frontier #04: Is Chain of Thought Real?
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Check library
Five ML Concepts - #13 ~ checkpointing
midi-cli-rs: Extending with Custom Mood Packs ~ chillout
Five ML Concepts - #28 ~ Chinchilla scaling laws
Saw #12: A Model That Decides, and an Index That Knows ~ Choice
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ chunks
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
Rabbit-hole #3: FORTH --- Life After Hashing ~ circular buffer
Personal Software #10: A Sudoku That Teaches You the Strategies ~ claiming
Five ML Concepts - #29 ~ class representation geometry
ML Frontier #01: Neural Collapse ~ class representations
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ classic BASIC games
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Claude Code cloud sessions
Cat Finder: Personal Software via Vibe Coding ~ Claude Code
Neural-Net-RS: An Educational Neural Network Platform ~ Claude Code
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ Claude Code
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ Claude Code
MCP: Teaching Claude to Play (and Trash Talk)
TBT #11: APL\360 Revisited ~ clean-room interpreter
Cat Finder: Personal Software via Vibe Coding ~ CLI tool
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ clippy-style linter
midi-cli-rs: Extending with Custom Mood Packs ~ CLI
midi-cli-rs: Music Generation for AI Coding Agents ~ CLI
music-pipe-rs: Unix Pipelines for MIDI Composition ~ CLI
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ clocked circuits
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ Clojure gcd
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ closed-issues heatmap
Saw #15: agentrail, Correcting the Record ~ close
Saw #15: agentrail, Correcting the Record ~ cloud agents
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Personal Software #10: A Sudoku That Teaches You the Strategies ~ clue digging
Lucy 20%: Upgrading My Home AI Cluster
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ CMD key
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ CMKEY
TBT #2: Pipelines on OS/390 ~ CMS Pipelines
Array Languages #11: Math Equations as X_eTaL Macros ~ CNN triple sum
Five ML Concepts - #10 ~ CNN
Machine Learning #9: Teaching an Array Language to Say CNN ~ CNN
Machine Learning #9: Teaching an Array Language to Say CNN
Made Visible #4: Rosetta M, a Stone with Four Faces ~ CNN
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ code metrics
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ code walkthrough
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ codegen bugs
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ coding agents
Welcome to Software Wrighter Lab ~ coding agents
AI Tools #7: A Coding Agent Small Enough to Understand ~ coding agent
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
AI Tools #7: A Coding Agent Small Enough to Understand
Cat Finder: Personal Software via Vibe Coding
midi-cli-rs: Music Generation for AI Coding Agents
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ coefficient training
Five ML Concepts - #14 ~ cold start problem
ML Frontier #01: Neural Collapse
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ colon definition
Made Visible #1: A Microkernel's Storage, Drawn ~ columnar contract
Made Visible #2: MesaOS, the Conventional One ~ columnar contract
Made Visible #3: MLOS, Where Memory Means Something Else ~ columnar contract
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ combinators
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ combinators
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ combinators
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ commit heatmap
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ compile mode
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ compile to Rust
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ compiler backend
Saw #5: Sagas, Languages, and Compiler Chains ~ compiler toolchain
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ compiler visualization
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Bucket List #1: Things I've Always Wanted to Build ~ compiler
Bucket List #2: A Landing Page for Software Tools ~ compiler
Saw #5: Sagas, Languages, and Compiler Chains
Array Languages #14: Types, Lints and Errors in X_eTaL ~ compile-time errors versus run-time errors
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ complect
pjmai-rs: Navigation History and Fuzzy Completion
music-pipe-rs: Unix Pipelines for MIDI Composition ~ composable tools
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ composite layer
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ compositional reasoning
music-pipe-rs: Unix Pipelines for MIDI Composition
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ compress
Five ML Concepts - #28 ~ compute optimality
Cat Finder: Personal Software via Vibe Coding ~ computer vision
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
Five ML Concepts - #17 ~ concept drift
Five ML Concepts - #10
Five ML Concepts - #11
Five ML Concepts - #12
Five ML Concepts - #13
Five ML Concepts - #14
Five ML Concepts - #15
Five ML Concepts - #16
Five ML Concepts - #17
Five ML Concepts - #18
Five ML Concepts - #19
Five ML Concepts - #1
Five ML Concepts - #20
Five ML Concepts - #21
Five ML Concepts - #22
Five ML Concepts - #23
Five ML Concepts - #24
Five ML Concepts - #25
Five ML Concepts - #26
Five ML Concepts - #27
Five ML Concepts - #28
Five ML Concepts - #29
Five ML Concepts - #2
Five ML Concepts - #30: The Journey So Far
Five ML Concepts - #3
Five ML Concepts - #4
Five ML Concepts - #5
Five ML Concepts - #6
Five ML Concepts - #7
Five ML Concepts - #8
Five ML Concepts - #9
Five ML Concepts - #28 ~ conditional computation
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers ~ conditional memory
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ conditional memory
ML Frontier #04: Is Chain of Thought Real? ~ conditional reasoning
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Five ML Concepts - #25 ~ confidence calibration
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ console panel
How AI Learns Part 6: Toward Continuous Learning ~ consolidation
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ constant dollars
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
Five ML Concepts - #26 ~ constitutional AI
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ content-addressed cache
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ context engineering
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers ~ context extension
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ context management
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ context management
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot ~ context rot
Five ML Concepts - #7 ~ context window
RLM: Recursive Language Models for Massive Context ~ context window
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
How AI Learns Part 5: Context Engineering & Recursive Reasoning
RLM: Recursive Language Models for Massive Context
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ continual learning
Five ML Concepts - #27 ~ continual learning
ML Frontier #01: Neural Collapse ~ continual learning
Multi-Hop Reasoning (2/2): The Distribution Trap ~ continual learning
Saw #11: Building a Tiny Mixture of Experts Microscope ~ continual learning
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ continual learning
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ continual learning
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ continuous convolution
How AI Learns Part 6: Toward Continuous Learning ~ continuous learning
How AI Learns Part 7: Designing a Continuous Learning Agent ~ continuous learning
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
How AI Learns Part 6: Toward Continuous Learning
How AI Learns Part 7: Designing a Continuous Learning Agent
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
Machine Learning #9: Teaching an Array Language to Say CNN ~ conv2d
Made Visible #2: MesaOS, the Conventional One
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ convolution versus cross-correlation
Five ML Concepts - #10 ~ convolutional neural network
Machine Learning #9: Teaching an Array Language to Say CNN ~ convolutional neural network
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
Machine Learning #9: Teaching an Array Language to Say CNN ~ convolution
Made Visible #4: Rosetta M, a Stone with Four Faces ~ convolution
Array Languages #1: X_eTaL, an Array Language You Can Read ~ Conway's Life one-liner
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
TBT #11: APL\360 Revisited ~ COR24 APL
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ COR24 BASIC
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ COR24 BASIC
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ COR24 emulator
Embedded #2: COR24-RS --- Learn Assembly in Your Browser
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ COR24-TB
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ COR24-TB
Bucket List #2: A Landing Page for Software Tools ~ COR24
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ COR24
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ COR24
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ COR24
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ COR24
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ COR24
Made Visible #1: A Microkernel's Storage, Drawn ~ COR24
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ COR24
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ COR24
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ COR24
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ COR24
Rabbit-hole #3: FORTH --- Life After Hashing ~ COR24
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ COR24
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ COR24
Saw #5: Sagas, Languages, and Compiler Chains ~ COR24
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ COR24
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ COR24
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ COR24
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
Saw #15: agentrail, Correcting the Record
Five ML Concepts - #19 ~ correlation vs causation
Five ML Concepts - #23 ~ cosine annealing
Five ML Concepts - #18 ~ cost vs quality tradeoffs
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
Five ML Concepts - #11 ~ CoT
ML Frontier #04: Is Chain of Thought Real? ~ CoT
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ count-based novelty
Five ML Concepts - #19 ~ covariate shift
Large-Language-Monkeys: Scaling Inference, Not Models ~ coverage
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ CPI
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ CPU rasterizer
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ cross-compilation
Array Languages #11: Math Equations as X_eTaL Macros ~ cross-correlation
Machine Learning #9: Teaching an Array Language to Say CNN ~ cross-correlation
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ cross-platform editor
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ cross-reference site
Five ML Concepts - #7 ~ cross-validation
TBT #3: Vector Graphics Games ~ CRT
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ cubelets as vectors
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ CUDA backend
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ CUDA vs ROCm vs Metal vs OpenCL
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ CUDA without nvcc
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ CUDA
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ curiosity-driven exploration
Five ML Concepts - #19 ~ curriculum learning
Five ML Concepts - #15 ~ curse of dimensionality
midi-cli-rs: Extending with Custom Mood Packs ~ custom moods
midi-cli-rs: Extending with Custom Mood Packs
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ cycle simulator
D
Five ML Concepts - #26 ~ data augmentation
Five ML Concepts - #17 ~ data drift
Five ML Concepts - #24 ~ data leakage
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ data notebook
Five ML Concepts - #22 ~ data scaling
JSON et al: A Deep Dive into Data Serialization Formats ~ data serialization
Made Visible #4: Rosetta M, a Stone with Four Faces ~ dataflow
TBT #2: Pipelines on OS/390 ~ dataflow
JSON et al: A Deep Dive into Data Serialization Formats
music-pipe-rs: Unix Pipelines for MIDI Composition ~ DAW
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ DAW
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ dead-leak
Bucket List #2: A Landing Page for Software Tools ~ debugger
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
Saw #12: A Model That Decides, and an Index That Knows
Saw #12: A Model That Decides, and an Index That Knows ~ decision trace
ML Frontier #02: In-Context Reinforcement Learning ~ decision transformer
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Array Languages #16: How X_eTaL Evolved, Decision by Decision
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ decomplect
Five ML Concepts - #30: The Journey So Far ~ deep learning
ML Frontier #01: Neural Collapse ~ deep learning
Deepseek Papers (1/3): mHC - Training Stability at Any Depth ~ deep networks
Large-Language-Monkeys: Scaling Inference, Not Models ~ DeepSeek-Coder
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
JSON et al: A Deep Dive into Data Serialization Formats
TBT #11: APL\360 Revisited ~ del editor
Five ML Concepts - #29 ~ delayed generalization
ML Frontier #05: Grokking --- Delayed Generalization ~ delayed generalization
ML Frontier #05: Grokking --- Delayed Generalization
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ demo site status tab
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ demo-combinators
Saw #12: A Model That Decides, and an Index That Knows ~ demo-decision-model
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ demo-decision-model
music-pipe-rs: Web Demo and Multi-Instrument Arrangements
Five ML Concepts - #30: The Journey So Far ~ deployment
How AI Learns Part 7: Designing a Continuous Learning Agent ~ deployment
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ design decisions
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ design patterns
How AI Learns Part 7: Designing a Continuous Learning Agent
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ dev image
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ developer tools
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Devstral
AI Tools #7: A Coding Agent Small Enough to Understand ~ Devstral
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ dictionary compaction
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ dictionary header
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ dictionary lookup
Rabbit-hole #3: FORTH --- Life After Hashing ~ dictionary
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
Personal Software #10: A Sudoku That Teaches You the Strategies ~ difficulty grading
Five ML Concepts - #8 ~ diffusion models
Five ML Concepts - #26 ~ dimensionality reduction
Five ML Concepts - #2 ~ direct preference optimization
How AI Learns Part 3: Weight-Based Learning ~ Direct Preference Optimization
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ directory navigation
Welcome to Software Wrighter Lab ~ Discord
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ DiscoveryOne
Five ML Concepts - #10 ~ distillation
How AI Learns Part 3: Weight-Based Learning ~ distillation
Saw #11: Building a Tiny Mixture of Experts Microscope ~ distillation
Multi-Hop Reasoning (2/2): The Distribution Trap ~ distribution matching
Five ML Concepts - #30: The Journey So Far ~ distribution shift
Five ML Concepts - #11 ~ distribution shift
Multi-Hop Reasoning (2/2): The Distribution Trap
Many-Eyes Learning: Intrinsic Rewards and Diversity
JSON et al: A Deep Dive into Data Serialization Formats
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Docent matcher
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ DOCOL
Small Models (3/6): Planner + Doer = Genius
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ dogfooding a language
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ dogfooding languages
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ dogfooding
AI Tools #7: A Coding Agent Small Enough to Understand ~ dogfooding
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ dogfooding
Saw #11: Building a Tiny Mixture of Experts Microscope ~ dogfooding
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ dollars per megabyte
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ domain-specific superintelligence
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Saw #15: agentrail, Correcting the Record ~ done elsewhere
Five ML Concepts - #25 ~ double descent
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Five ML Concepts - #2 ~ DPO
How AI Learns Part 3: Weight-Based Learning ~ DPO
Solving Sparse Rewards with Many Eyes ~ DQN
Made Visible #1: A Microkernel's Storage, Drawn
Five ML Concepts - #15 ~ drift detection
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Five ML Concepts - #30: The Journey So Far ~ dropout
Five ML Concepts - #6 ~ dropout
Five ML Concepts - #9 ~ dropout
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ DS3231 RTC
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ DSS
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ dual memory
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ Dyalog APL
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Dyalog dfns
TBT #11: APL\360 Revisited ~ Dyalog
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Five ML Concepts - #28 ~ dynamic routing
DyTopo: Dynamic Topology for Multi-Agent AI ~ dynamic topology
DyTopo: Dynamic Topology for Multi-Agent AI
DyTopo: Dynamic Topology for Multi-Agent AI ~ DyTopo
DyTopo: Dynamic Topology for Multi-Agent AI
E
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ eager evaluation
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Five ML Concepts - #13 ~ early stopping
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ earthquakes
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ eating your own dog food
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ edit lock
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ editors timeline
Bucket List #2: A Landing Page for Software Tools ~ editor
Saw #15: agentrail, Correcting the Record ~ edit
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ educational programming
TBT #4: ToonTalk - Teaching Robots to Program ~ educational programming
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ educational tools
Neural-Net-RS: An Educational Neural Network Platform
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ educational
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ EEPROM simulator
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ EEVEE
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ EEVEE
Small Models (1/6): 976 Parameters Beat Billions ~ efficiency
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ efficient frontier
How AI Learns Part 6: Toward Continuous Learning ~ Efficient Lifelong Learning Algorithm
Small Models (5/6): Max AI Per Watt ~ efficient LLM
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ efficient LLM
Five ML Concepts - #28 ~ efficient scaling
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ Eigencube
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
Array Languages #11: Math Equations as X_eTaL Macros ~ einsum
Five ML Concepts - #27 ~ elastic weight consolidation
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ electronics
midi-cli-rs: Extending with Custom Mood Packs ~ electronic
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ ELF loader
Made Visible #2: MesaOS, the Conventional One ~ ELF
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ elisp
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ elisp
Saw #12: A Model That Decides, and an Index That Knows ~ ELIZA
Small Models (2/6): AI in Your Pocket ~ Eliza
How AI Learns Part 6: Toward Continuous Learning ~ ELLA
Made Visible #3: MLOS, Where Memory Means Something Else
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ Emacs glyph entry
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ Emacs graphics
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ emacs integration
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Emacs org-mode
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ Emacs
Saw #11: Building a Tiny Mixture of Experts Microscope ~ embedded inference
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ embedded languages
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ embedded Rust
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ embedded segments
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ embedded systems
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ embedded systems
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ embedded VM
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ embedded-hal
Bucket List #1: Things I've Always Wanted to Build ~ embedded
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Embedded #2: COR24-RS --- Learn Assembly in Your Browser
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Five ML Concepts - #1 ~ embeddings
Five ML Concepts - #23 ~ emergent behavior
Five ML Concepts - #23 ~ emergent capabilities
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ EMS expanded memory
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ emufpga
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
Bucket List #1: Things I've Always Wanted to Build ~ emulator
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ emulator
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ emulator
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ emulator
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
Five ML Concepts - #10 ~ encoder-decoder
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ endless world
Energy-Based Learning: From Hopfield Networks to JEPA ~ energy based models
Energy-Based Learning: From Hopfield Networks to JEPA
How AI Learns Part 5: Context Engineering & Recursive Reasoning
In-Context Learning Revisited: From Mystery to Engineering
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ engram
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
How AI Learns Part 4: Memory-Based Learning ~ Engram
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ Engram
Saw #11: Building a Tiny Mixture of Experts Microscope ~ Engram
AI Tools #7: A Coding Agent Small Enough to Understand
Five ML Concepts - #18 ~ ensembling
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ entity-component system as arrays
Five ML Concepts - #18 ~ epoch
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ epsilon decay
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ equation macros
Array Languages #11: Math Equations as X_eTaL Macros
ML Frontier #01: Neural Collapse ~ equiangular tight frame
Array Languages #14: Types, Lints and Errors in X_eTaL ~ ergonomics
Array Languages #14: Types, Lints and Errors in X_eTaL ~ error messages
Array Languages #14: Types, Lints and Errors in X_eTaL
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ ESP32 PSRAM
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ Espanso text expander
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ Espanso
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ essential complexity
music-pipe-rs: Unix Pipelines for MIDI Composition ~ Euclidean rhythm
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ Euclidean rhythm
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
How AI Learns Part 7: Designing a Continuous Learning Agent ~ evaluation
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Five ML Concepts - #27 ~ EWC
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ execute
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Rabbit-hole #3: FORTH --- Life After Hashing ~ execution count
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ exit codes
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ EXIT
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ experience bank
Five ML Concepts - #27 ~ experience replay
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ experiences
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
Array Languages #1: X_eTaL, an Array Language You Can Read ~ eXperimental Extensible Typed Array Language
Saw #11: Building a Tiny Mixture of Experts Microscope ~ expert cache
Saw #11: Building a Tiny Mixture of Experts Microscope ~ expert specialization
Saw #11: Building a Tiny Mixture of Experts Microscope
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ exploration strategies
Solving Sparse Rewards with Many Eyes ~ exploration strategies
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ exposed faces
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Array Languages #4: X_eTaL-extensions, Extending the Machine
midi-cli-rs: Extending with Custom Mood Packs
midi-cli-rs: Extending with Custom Mood Packs ~ extensibility
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ extension ABI V1
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Five ML Concepts - #27 ~ external memory
How AI Learns Part 4: Memory-Based Learning ~ external memory
Solving Sparse Rewards with Many Eyes
F
Made Visible #4: Rosetta M, a Stone with Four Faces
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Five ML Concepts - #19 ~ failure analysis
ML Frontier #04: Is Chain of Thought Real? ~ faithfulness
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ falling blocks
Five ML Concepts - #30: The Journey So Far
ML Frontier #01: Neural Collapse ~ feature collapse
Five ML Concepts - #25 ~ feature learning
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ features not adopted
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Five ML Concepts - #29 ~ feedback loops
How AI Learns Part 7: Designing a Continuous Learning Agent ~ feedback loops
Five ML Concepts - #10 ~ few-shot learning
In-Context Learning Revisited: From Mystery to Engineering ~ few-shot learning
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ Ffi.xtlm
rank-wav: Ranking Audio Files by Acoustic Quality ~ FFT
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ file processing
rank-wav: Ranking Audio Files by Acoustic Quality
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ find greatest common divisor of array
Cat Finder: Personal Software via Vibe Coding
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ FIND
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
Rabbit-hole #3: FORTH --- Life After Hashing ~ FIND
Bucket List #1: Things I've Always Wanted to Build ~ fine-tuning
Five ML Concepts - #3 ~ fine-tuning
How AI Learns Part 1: The Many Meanings of Learning ~ fine-tuning
How AI Learns Part 3: Weight-Based Learning ~ fine-tuning
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs ~ fine-tuning
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ fine-tuning
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
TBT #1: My First Program Was a Horse Race
Five ML Concepts - #27 ~ Fisher information
Small Models (6/6): Which Small AI Fits YOUR Laptop?
Five ML Concepts - #30: The Journey So Far ~ five ML concepts series
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Five ML Concepts - #10
Five ML Concepts - #11
Five ML Concepts - #12
Five ML Concepts - #13
Five ML Concepts - #14
Five ML Concepts - #15
Five ML Concepts - #16
Five ML Concepts - #17
Five ML Concepts - #18
Five ML Concepts - #19
Five ML Concepts - #1
Five ML Concepts - #20
Five ML Concepts - #21
Five ML Concepts - #22
Five ML Concepts - #23
Five ML Concepts - #24
Five ML Concepts - #25
Five ML Concepts - #26
Five ML Concepts - #27
Five ML Concepts - #28
Five ML Concepts - #29
Five ML Concepts - #2
Five ML Concepts - #30: The Journey So Far
Five ML Concepts - #3
Five ML Concepts - #4
Five ML Concepts - #5
Five ML Concepts - #6
Five ML Concepts - #7
Five ML Concepts - #8
Five ML Concepts - #9
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ fixed point
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ fixed point
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ fixed point
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ fixups
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Five ML Concepts - #9 ~ Flash Attention
Made Visible #1: A Microkernel's Storage, Drawn ~ FlashViz
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ flat file
Five ML Concepts - #23 ~ flat minima
Five ML Concepts - #29 ~ flat minima
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ flowing water
midi-cli-rs: Music Generation for AI Coding Agents ~ FluidSynth
Lucy 20%: Upgrading My Home AI Cluster ~ FLUX schnell
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ forcing function
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ forcing function
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ forcing function
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ fork combinator
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
JSON et al: A Deep Dive into Data Serialization Formats
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ Forte Software
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ Forth composer
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ Forth composer
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ Forth kernel
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Forth parsing words
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ Forth self-hosting
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ forth-from-forth
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ forth-from-forth
Rabbit-hole #3: FORTH --- Life After Hashing ~ forth-from-forth
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ forth-from-forth
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ forth-in-forth
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ forth-in-forth
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ forth-on-forthish
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ forth-on-forthish
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ Forth
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ Forth
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
Rabbit-hole #3: FORTH --- Life After Hashing ~ Forth
Rabbit-hole #3: FORTH --- Life After Hashing
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ Forth
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ Forth
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ Fortran compiler
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ forward references
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
Made Visible #4: Rosetta M, a Stone with Four Faces ~ four faces
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ four tools
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Fourier epicycles
Made Visible #4: Rosetta M, a Stone with Four Faces
Saw #5: Sagas, Languages, and Compiler Chains ~ FPGA soft CPU
Bucket List #1: Things I've Always Wanted to Build ~ FPGA
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ FPGA
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ FPGA
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ FPGA
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ Fred Brooks
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ free list
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ Freedreno IR3
Saw #11: Building a Tiny Mixture of Experts Microscope ~ FreeToken
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Five ML Concepts - #30: The Journey So Far ~ frontier ML thinking
ML Frontier #01: Neural Collapse
ML Frontier #02: In-Context Reinforcement Learning
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
ML Frontier #04: Is Chain of Thought Real?
ML Frontier #05: Grokking --- Delayed Generalization
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ frustum culling
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ function LOC
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ functional pearl
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ functional pipelines
Array Languages #17: What Makes a Practical Language, IMHO ~ functional programming
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ fuzz testing
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ fuzzit
pjmai-rs: Navigation History and Fuzzy Completion ~ fuzzy completion
pjmai-rs: Navigation History and Fuzzy Completion
G
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ Game of Life
MCP: Teaching Claude to Play (and Trash Talk) ~ game server
TBT #3: Vector Graphics Games
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ GarageBand
Bucket List #2: A Landing Page for Software Tools ~ garbage collector
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ garbage collector
Five ML Concepts - #21 ~ gated recurrent unit
Five ML Concepts - #11 ~ gated recurrent unit
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ gating mechanism
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ gcd min max
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ gc-slack
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ Gemini
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ Gemma-2B
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Gemma-4
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ Gemma
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Gemma
Five ML Concepts - #16 ~ generalization
ML Frontier #01: Neural Collapse ~ generalization
ML Frontier #05: Grokking --- Delayed Generalization
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
midi-cli-rs: Music Generation for AI Coding Agents
Five ML Concepts - #24 ~ generative models
midi-cli-rs: Extending with Custom Mood Packs ~ generative music
music-pipe-rs: Unix Pipelines for MIDI Composition ~ generative music
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ generative music
Five ML Concepts - #7 ~ generative pre-trained transformer
Small Models (3/6): Planner + Doer = Genius
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ GF(2)
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ GGUF
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ GGUF
Small Models (2/6): AI in Your Pocket ~ GGUF
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ gh gist create
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ git history
Saw #15: agentrail, Correcting the Record ~ git history
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ git pre-commit hook
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ git storage
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ git-friendly testing
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ GitHub CLI gist
Personal Software #11: A Campus for the Public Work ~ GitHub organizations
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ GitHub profile README
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ GitHub Wiki
Welcome to Software Wrighter Lab ~ GitHub
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ git
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ GLM-5
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ glTF export
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ glyph input
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ GNU APL
TBT #1: My First Program Was a Horse Race ~ GNU APL
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ golden file testing
Five ML Concepts - #26 ~ Goodhart's law
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Gowin FPGAs
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ Gowin
In-Context Learning Revisited: From Mystery to Engineering ~ GPT-3
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ GPT-4o
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ gpt-oss-20b
Five ML Concepts - #7 ~ GPT
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ GPU native extension
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ GPU toolchain comparison
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Five ML Concepts - #7 ~ GQA
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ grade
Five ML Concepts - #14 ~ gradient clipping
Five ML Concepts - #2 ~ gradient descent
In-Context Learning Revisited: From Mystery to Engineering ~ gradient descent
Five ML Concepts - #20 ~ gradient noise
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
TBT #3: Vector Graphics Games
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ GraphMERT
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ green screen terminal
Five ML Concepts - #29 ~ grokking
ML Frontier #05: Grokking --- Delayed Generalization ~ grokking
ML Frontier #05: Grokking --- Delayed Generalization
Large-Language-Monkeys: Scaling Inference, Not Models ~ Groq
Five ML Concepts - #7 ~ grouped query attention
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Five ML Concepts - #21 ~ GRU
Five ML Concepts - #11 ~ GRU
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ GTX 1660 Super
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
H
Five ML Concepts - #1 ~ hallucination
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ hash-based memory
Saw #12: A Model That Decides, and an Index That Knows ~ hashed features
Rabbit-hole #3: FORTH --- Life After Hashing
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ Haskell liftM2 point-free
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ Haskell types
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ heap budget
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ heap exhaustion
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ heap_justification
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ HEX1000
Made Visible #2: MesaOS, the Conventional One ~ HHDM
Personal Software #10: A Sudoku That Teaches You the Strategies ~ hidden pair
Personal Software #10: A Sudoku That Teaches You the Strategies ~ hidden single
Array Languages #1: X_eTaL, an Array Language You Can Read ~ Hindley-Milner
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
pjmai-rs: Navigation History and Fuzzy Completion
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ Hollerith
Lucy 20%: Upgrading My Home AI Cluster ~ home AI cluster
Lucy 20%: Upgrading My Home AI Cluster ~ homelab
Lucy 20%: Upgrading My Home AI Cluster
Energy-Based Learning: From Hopfield Networks to JEPA ~ Hopfield network
Energy-Based Learning: From Hopfield Networks to JEPA
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ horse race APL
TBT #1: My First Program Was a Horse Race
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ hotkey expansion
Rabbit-hole #3: FORTH --- Life After Hashing ~ hot-token cache
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
How AI Learns Part 1: The Many Meanings of Learning
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
How AI Learns Part 3: Weight-Based Learning
How AI Learns Part 4: Memory-Based Learning
How AI Learns Part 5: Context Engineering & Recursive Reasoning
How AI Learns Part 6: Toward Continuous Learning
How AI Learns Part 7: Designing a Continuous Learning Agent
Saw #11: Building a Tiny Mixture of Experts Microscope ~ HRM
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ HTTP client
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ HTTP fetch
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ HTTP server
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ HuggingFace integration
Five ML Concepts - #20 ~ human-in-the-loop
music-pipe-rs: Unix Pipelines for MIDI Composition ~ humanize
I
Bucket List #1: Things I've Always Wanted to Build
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ I2C COR24 emulator
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ I2C pluggable devices
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ I2C
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ I2C
TBT #11: APL\360 Revisited ~ I-beams
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ IBM 029
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM 1130 core memory words
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ IBM 1130
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ IBM 1442
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM 1800
TBT #3: Vector Graphics Games ~ IBM 2250
TBT #1: My First Program Was a Horse Race ~ IBM 2741
TBT #11: APL\360 Revisited ~ IBM 2741
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM 308X 4MB
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM 3090 Model 200
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ IBM 3270
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM 5100 64K
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ IBM 5100
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ IBM 5110
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ IBM 5120
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ IBM internal tools
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ IBM mainframe
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ IBM PC 640K
TBT #2: Pipelines on OS/390 ~ IBM S/390
TBT #11: APL\360 Revisited ~ IBM System/360
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ IBM
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Five ML Concepts - #5 ~ ICL
How AI Learns Part 1: The Many Meanings of Learning ~ ICL
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ ICL
In-Context Learning Revisited: From Mystery to Engineering ~ ICL
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ ICRL
ML Frontier #02: In-Context Reinforcement Learning ~ ICRL
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ ICRL
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ ICRL
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ IDE timeline
Energy-Based Learning: From Hopfield Networks to JEPA ~ I-JEPA
Machine Learning #9: Teaching an Array Language to Say CNN ~ im2col
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ image pipeline
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
Array Languages #17: What Makes a Practical Language, IMHO
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ implicit reward model
Saw #11: Building a Tiny Mixture of Experts Microscope ~ in-browser training
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ include
Five ML Concepts - #5 ~ in-context learning
How AI Learns Part 1: The Many Meanings of Learning ~ in-context learning
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ in-context learning
In-Context Learning Revisited: From Mystery to Engineering ~ in-context learning
ML Frontier #02: In-Context Reinforcement Learning ~ in-context learning
ML Frontier #02: In-Context Reinforcement Learning ~ in-context reinforcement learning
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ in-context reinforcement learning
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ in-context reinforcement learning
ML Frontier #02: In-Context Reinforcement Learning
In-Context Learning Revisited: From Mystery to Engineering
Saw #12: A Model That Decides, and an Index That Knows
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ indicator lights
In-Context Learning Revisited: From Mystery to Engineering ~ induction heads
Five ML Concepts - #12 ~ inductive bias
Five ML Concepts - #26 ~ inference latency
Five ML Concepts - #28 ~ inference parallelism
Large-Language-Monkeys: Scaling Inference, Not Models ~ inference scaling
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ inference-time learning
Five ML Concepts - #9 ~ inference
Large-Language-Monkeys: Scaling Inference, Not Models
Large-Language-Monkeys: Scaling Inference, Not Models ~ infinite monkey theorem
Personal Software #11: A Campus for the Public Work ~ information architecture
Solving Sparse Rewards with Many Eyes ~ information bottleneck
Deepseek Papers (1/3): mHC - Training Stability at Any Depth ~ initialization
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ inner product
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ insert
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
Rabbit-hole #3: FORTH --- Life After Hashing ~ instrumentation
Saw #11: Building a Tiny Mixture of Experts Microscope ~ INT4
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ integer Smalltalk
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ integer-only BASIC
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
Five ML Concepts - #25 ~ interpolation threshold
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ interpret mode
Five ML Concepts - #20 ~ interpretability
Small Models (4/6): This AI Has a Visible Brain ~ interpretable AI
Bucket List #2: A Landing Page for Software Tools ~ interpreter
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ interrupt register
JSON et al: A Deep Dive into Data Serialization Formats
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ intrinsic rewards
Many-Eyes Learning: Intrinsic Rewards and Diversity
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ IPC
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ ISA translation
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Personal Software #11: A Campus for the Public Work ~ isometric map
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ ISPF
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ issue tracker
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ Iverson suggestivity
J
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ J addons
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ J fork
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ J hook
Five ML Concepts - #21 ~ jailbreaks
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
midi-cli-rs: Music Generation for AI Coding Agents ~ jazz
Energy-Based Learning: From Hopfield Networks to JEPA ~ JEPA
Energy-Based Learning: From Hopfield Networks to JEPA
Small Models (2/6): AI in Your Pocket ~ Jetpack Compose
Saw #12: A Model That Decides, and an Index That Knows ~ Jev
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Jev
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ JIT compiler
Small Models (2/6): AI in Your Pocket ~ JNI
Energy-Based Learning: From Hopfield Networks to JEPA ~ Joint Embedding Predictive Architecture
Five ML Concepts - #30: The Journey So Far
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ jregress
JSON et al: A Deep Dive into Data Serialization Formats ~ JSONB
JSON et al: A Deep Dive into Data Serialization Formats ~ JSONL
MCP: Teaching Claude to Play (and Trash Talk) ~ JSON-RPC
JSON et al: A Deep Dive into Data Serialization Formats ~ JSON
JSON et al: A Deep Dive into Data Serialization Formats
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Julia sets
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ JuliaMono
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
K
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ Kate editor syntax highlighting
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
TBT #4: ToonTalk - Teaching Robots to Program ~ Ken Kahn
TBT #1: My First Program Was a Horse Race ~ Kenneth Iverson
TBT #11: APL\360 Revisited ~ Kenneth Iverson
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Kepler
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ kernel fusion
Made Visible #2: MesaOS, the Conventional One ~ kernel heap
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ kernel sandbox
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ keypunch
Five ML Concepts - #8 ~ key-value cache
Five ML Concepts - #7 ~ k-fold
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ kgen.compile_offload
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ k-means
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ knowledge distillation
Five ML Concepts - #27 ~ knowledge editing
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ knowledge graphs
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs ~ knowledge graphs
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Saw #12: A Model That Decides, and an Index That Knows
TBT #6: PJMAI-RS - A Shell That Knows Your Projects
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ KSyntaxHighlighting XML
Made Visible #3: MLOS, Where Memory Means Something Else ~ KV blocks
Five ML Concepts - #8 ~ KV cache
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ Kyle Croarkin
L
Five ML Concepts - #17 ~ L2 regularization
Five ML Concepts - #6 ~ L2 weight decay
Five ML Concepts - #25 ~ label smoothing
Welcome to Software Wrighter Lab
Saw #12: A Model That Decides, and an Index That Knows ~ LanceDB
Bucket List #2: A Landing Page for Software Tools
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Landlock
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ lanes
Saw #1: pjmai-rs, Rig, and langchain-rust ~ langchain-rust
Saw #1: pjmai-rs, Rig, and langchain-rust
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Langton's ant
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ language building
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ language design collaboration
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ language evolution
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ language extensions
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ language I/O examples
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ language implementation
ML Frontier #04: Is Chain of Thought Real? ~ language models
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ language playground
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Array Languages #11: Math Equations as X_eTaL Macros
Array Languages #12: ML Pipelines as X_eTaL Macros
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
Array Languages #14: Types, Lints and Errors in X_eTaL
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Array Languages #17: What Makes a Practical Language, IMHO
Array Languages #1: X_eTaL, an Array Language You Can Read
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Array Languages #4: X_eTaL-extensions, Extending the Machine
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
Array Languages #6: X_eTaL-games, Rules That Are Arrays
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Saw #5: Sagas, Languages, and Compiler Chains
Array Languages #1: X_eTaL, an Array Language You Can Read
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Array Languages #17: What Makes a Practical Language, IMHO
Machine Learning #9: Teaching an Array Language to Say CNN
RLM: Recursive Language Models for Massive Context
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Small Models (6/6): Which Small AI Fits YOUR Laptop?
RLM: Recursive Language Models for Massive Context ~ large context
Large-Language-Monkeys: Scaling Inference, Not Models ~ Large Language Monkeys
Large-Language-Monkeys: Scaling Inference, Not Models
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ lark
Five ML Concepts - #12 ~ latency
ML Frontier #04: Is Chain of Thought Real? ~ latent reasoning
Five ML Concepts - #5 ~ latent space
Array Languages #11: Math Equations as X_eTaL Macros ~ LaTeX from code
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ LaTeX from code
Array Languages #12: ML Pipelines as X_eTaL Macros ~ layer norm
How AI Learns Part 7: Designing a Continuous Learning Agent ~ layered architecture
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ lazy parameters
ML Frontier #05: Grokking --- Delayed Generalization ~ lazy training
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ lead image check
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ Learn library
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ learning new things
Five ML Concepts - #23 ~ learning rate schedules
Five ML Concepts - #24 ~ learning rate warmup
Five ML Concepts - #2 ~ learning rate
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
Energy-Based Learning: From Hopfield Networks to JEPA
How AI Learns Part 1: The Many Meanings of Learning
How AI Learns Part 3: Weight-Based Learning
How AI Learns Part 4: Memory-Based Learning
How AI Learns Part 6: Toward Continuous Learning
How AI Learns Part 7: Designing a Continuous Learning Agent
In-Context Learning Revisited: From Mystery to Engineering
ML Frontier #02: In-Context Reinforcement Learning
Machine Learning #9: Teaching an Array Language to Say CNN
Many-Eyes Learning: Intrinsic Rewards and Diversity
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
How AI Learns Part 1: The Many Meanings of Learning
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
How AI Learns Part 3: Weight-Based Learning
How AI Learns Part 4: Memory-Based Learning
How AI Learns Part 5: Context Engineering & Recursive Reasoning
How AI Learns Part 6: Toward Continuous Learning
How AI Learns Part 7: Designing a Continuous Learning Agent
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Embedded #2: COR24-RS --- Learn Assembly in Your Browser
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ LeetCode 1979
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ lexer animation
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ lexer parser
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ libraries
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ LicheeRV Nano
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Life microscope
Bucket List #1: Things I've Always Wanted to Build ~ lifelong learning
How AI Learns Part 6: Toward Continuous Learning ~ lifelong learning
Rabbit-hole #3: FORTH --- Life After Hashing
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ lighting
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ lights out
Made Visible #2: MesaOS, the Conventional One ~ limine
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ linear algebra
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ linear algebra
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ line-numbered BASIC
Bucket List #2: A Landing Page for Software Tools ~ linker
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ linter
Array Languages #14: Types, Lints and Errors in X_eTaL
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
Bucket List #2: A Landing Page for Software Tools ~ Lisp
Bucket List #1: Things I've Always Wanted to Build
Bucket List #2: A Landing Page for Software Tools
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
AI Tools #7: A Coding Agent Small Enough to Understand ~ literate programming
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ literate programming
Large-Language-Monkeys: Scaling Inference, Not Models ~ Llama 3
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ llama.cpp
Small Models (5/6): Max AI Per Watt ~ Llama-3.2-1B
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ llama-server
Saw #1: pjmai-rs, Rig, and langchain-rust ~ llm agents
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot ~ LLM failure modes
How AI Learns Part 1: The Many Meanings of Learning ~ LLM learning
ML Frontier #05: Grokking --- Delayed Generalization ~ LLM pretraining
RLM: Recursive Language Models for Massive Context ~ LLM tools
AI Tools #7: A Coding Agent Small Enough to Understand ~ llm_call
ML Frontier #04: Is Chain of Thought Real? ~ LLMs
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ LLVM NVPTX
Saw #11: Building a Tiny Mixture of Experts Microscope ~ load balance
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ load plan
Lucy 20%: Upgrading My Home AI Cluster ~ local AI
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ local LLM agents
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ local LLM agent
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ local LLM
AI Tools #7: A Coding Agent Small Enough to Understand ~ local LLM
Cat Finder: Personal Software via Vibe Coding ~ local ML
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ local-llm-loop
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
How AI Learns Part 7: Designing a Continuous Learning Agent ~ logging
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers ~ long context
Five ML Concepts - #22 ~ Long Short-Term Memory
Five ML Concepts - #11 ~ long short-term memory
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ long-term recall
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ lookaside cache
Rabbit-hole #3: FORTH --- Life After Hashing ~ lookup optimization
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ loop wall-clock
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ LoRA routing
Five ML Concepts - #3 ~ LoRA
How AI Learns Part 1: The Many Meanings of Learning ~ LoRA
How AI Learns Part 3: Weight-Based Learning ~ LoRA
How AI Learns Part 7: Designing a Continuous Learning Agent ~ LoRA
Small Models (5/6): Max AI Per Watt ~ LoRA
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ LoRA
Five ML Concepts - #3 ~ loss function
Five ML Concepts - #14 ~ loss landscapes
Five ML Concepts - #23 ~ loss surface sharpness
Made Visible #4: Rosetta M, a Stone with Four Faces ~ loss trace
Five ML Concepts - #28 ~ lottery ticket hypothesis
Energy-Based Learning: From Hopfield Networks to JEPA ~ low energy optimization
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ low-bit inference
Five ML Concepts - #3 ~ low-rank adaptation
How AI Learns Part 1: The Many Meanings of Learning ~ Low-Rank Adaptation
How AI Learns Part 3: Weight-Based Learning ~ Low-Rank Adaptation
How AI Learns Part 7: Designing a Continuous Learning Agent ~ Low-Rank Adaptation
Small Models (5/6): Max AI Per Watt ~ Low-Rank Adaptation
Saw #11: Building a Tiny Mixture of Experts Microscope ~ low-rank experts
Five ML Concepts - #22 ~ LSTM
Five ML Concepts - #11 ~ LSTM
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Luckfox Pico
Lucy 20%: Upgrading My Home AI Cluster ~ Lucy AI
Lucy 20%: Upgrading My Home AI Cluster
TBT #3: Vector Graphics Games ~ Lunar Lander
M
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ M1 Max
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ M1 Max
Five ML Concepts - #1 ~ machine learning concepts
Five ML Concepts - #21 ~ machine learning concepts
Five ML Concepts - #22 ~ machine learning concepts
Five ML Concepts - #23 ~ machine learning concepts
Five ML Concepts - #24 ~ machine learning concepts
Five ML Concepts - #25 ~ machine learning concepts
Five ML Concepts - #26 ~ machine learning concepts
Five ML Concepts - #27 ~ machine learning concepts
Five ML Concepts - #28 ~ machine learning concepts
Five ML Concepts - #29 ~ machine learning concepts
Five ML Concepts - #2 ~ machine learning concepts
Five ML Concepts - #30: The Journey So Far ~ machine learning concepts
Five ML Concepts - #3 ~ machine learning concepts
Five ML Concepts - #4 ~ machine learning concepts
Five ML Concepts - #5 ~ machine learning concepts
Five ML Concepts - #6 ~ machine learning concepts
Five ML Concepts - #7 ~ machine learning concepts
Five ML Concepts - #8 ~ machine learning concepts
Five ML Concepts - #9 ~ machine learning concepts
Five ML Concepts - #10 ~ machine learning concepts
Five ML Concepts - #11 ~ machine learning concepts
Five ML Concepts - #12 ~ machine learning concepts
Five ML Concepts - #13 ~ machine learning concepts
Five ML Concepts - #14 ~ machine learning concepts
Five ML Concepts - #15 ~ machine learning concepts
Five ML Concepts - #16 ~ machine learning concepts
Five ML Concepts - #17 ~ machine learning concepts
Five ML Concepts - #18 ~ machine learning concepts
Five ML Concepts - #19 ~ machine learning concepts
Five ML Concepts - #20 ~ machine learning concepts
Neural-Net-RS: An Educational Neural Network Platform ~ machine learning education
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ machine learning in an array language
Saw #5: Sagas, Languages, and Compiler Chains ~ machine learning language
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ machine learning
Array Languages #4: X_eTaL-extensions, Extending the Machine
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
Machine Learning #9: Teaching an Array Language to Say CNN
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ macro argument parsing
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ macro contracts
Array Languages #14: Types, Lints and Errors in X_eTaL ~ macro errors
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ macro hygiene
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ macro hygiene
Array Languages #17: What Makes a Practical Language, IMHO ~ macros and extensions
Array Languages #11: Math Equations as X_eTaL Macros ~ macros instead of syntax
Array Languages #12: ML Pipelines as X_eTaL Macros ~ macros instead of syntax
Array Languages #11: Math Equations as X_eTaL Macros
Array Languages #12: ML Pipelines as X_eTaL Macros
Saw #5: Sagas, Languages, and Compiler Chains ~ macros
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Made Visible #1: A Microkernel's Storage, Drawn
Made Visible #2: MesaOS, the Conventional One
Made Visible #3: MLOS, Where Memory Means Something Else
Made Visible #4: Rosetta M, a Stone with Four Faces
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ mailboxes
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ mainframe
TBT #2: Pipelines on OS/390 ~ mainframe
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ maintenance mode
Large-Language-Monkeys: Scaling Inference, Not Models ~ majority voting
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ MakerLisp
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ MakerLisp
Array Languages #17: What Makes a Practical Language, IMHO
Five ML Concepts - #1 ~ Mamba SSM
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Mandelbrot
Five ML Concepts - #26 ~ manifold hypothesis
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ many decades
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ many-eyes learning
Many-Eyes Learning: Intrinsic Rewards and Diversity
How AI Learns Part 1: The Many Meanings of Learning
Solving Sparse Rewards with Many Eyes
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ Mario Zechner
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ masks
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ Mass Compile
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ Mass Compile
RLM: Recursive Language Models for Massive Context
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
Array Languages #11: Math Equations as X_eTaL Macros ~ math notation in an array language
Made Visible #4: Rosetta M, a Stone with Four Faces ~ math notation visualization trace
Array Languages #11: Math Equations as X_eTaL Macros
Machine Learning #9: Teaching an Array Language to Say CNN ~ matmul
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Matrix
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Maxwell
Small Models (5/6): Max AI Per Watt
Small Models (1/6): 976 Parameters Beat Billions ~ maze solving
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ McCallum memory prices
MCP: Teaching Claude to Play (and Trash Talk)
How AI Learns Part 1: The Many Meanings of Learning
Made Visible #3: MLOS, Where Memory Means Something Else
Five ML Concepts - #29 ~ mechanistic interpretability
ML Frontier #05: Grokking --- Delayed Generalization ~ mechanistic interpretability
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
ML Frontier #05: Grokking --- Delayed Generalization ~ memorization
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ memory layer
Made Visible #1: A Microkernel's Storage, Drawn ~ memory layout visualization
Made Visible #2: MesaOS, the Conventional One ~ memory layout visualization
Made Visible #3: MLOS, Where Memory Means Something Else ~ memory layout visualization
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ memory layout
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ memory management
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ memory profiles
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers ~ memory retrieval
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ memory size history
Five ML Concepts - #27 ~ memory-augmented networks
How AI Learns Part 4: Memory-Based Learning
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Made Visible #3: MLOS, Where Memory Means Something Else
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ merge conflict markers
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ MesaOS
Made Visible #2: MesaOS, the Conventional One ~ MesaOS
Made Visible #2: MesaOS, the Conventional One
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ mesh from arrays
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ message passing
JSON et al: A Deep Dive into Data Serialization Formats ~ MessagePack
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ meta-circular
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ Metal AIR
In-Context Learning Revisited: From Mystery to Engineering ~ meta-learning
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ Metal
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Bucket List #1: Things I've Always Wanted to Build ~ microcontrollers
Made Visible #1: A Microkernel's Storage, Drawn
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ microkernel
Saw #11: Building a Tiny Mixture of Experts Microscope ~ MicroMoE
Saw #11: Building a Tiny Mixture of Experts Microscope
midi-cli-rs: Extending with Custom Mood Packs
midi-cli-rs: Music Generation for AI Coding Agents
midi-cli-rs: Extending with Custom Mood Packs ~ MIDI
midi-cli-rs: Music Generation for AI Coding Agents ~ MIDI
music-pipe-rs: Unix Pipelines for MIDI Composition ~ MIDI
music-pipe-rs: Unix Pipelines for MIDI Composition
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ MIDI
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ mid-saga
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ MIKROE Pressure 21 Click
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Milk-V Duo
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ Minesweeper
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ minicomputer
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ minimal coding agent
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ minimal kernel
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ MINIX
Five ML Concepts - #25 ~ miscalibration
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Mistral
RLM: Recursive Language Models for Massive Context ~ MIT
Five ML Concepts - #8 ~ mixed precision training
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ mixture of experts
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ mixture of experts
Five ML Concepts - #27 ~ mixture of experts
Five ML Concepts - #28 ~ mixture of experts
Five ML Concepts - #11 ~ mixture of experts
Saw #11: Building a Tiny Mixture of Experts Microscope ~ mixture of experts
Saw #11: Building a Tiny Mixture of Experts Microscope
Array Languages #12: ML Pipelines as X_eTaL Macros ~ ML data flow left to right
Five ML Concepts - #30: The Journey So Far ~ ML education
Array Languages #11: Math Equations as X_eTaL Macros ~ ML equations as code
Five ML Concepts - #18 ~ ML fragility
Made Visible #4: Rosetta M, a Stone with Four Faces ~ ML glyphs
Made Visible #3: MLOS, Where Memory Means Something Else ~ ML operating system
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ ML study group
Five ML Concepts - #8 ~ MLA
Five ML Concepts - #21 ~ MLOps
Five ML Concepts - #22 ~ MLOps
Five ML Concepts - #23 ~ MLOps
Five ML Concepts - #24 ~ MLOps
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ MLOS
Made Visible #3: MLOS, Where Memory Means Something Else ~ MLOS
Made Visible #3: MLOS, Where Memory Means Something Else
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ MLOS
AI Tools #7: A Coding Agent Small Enough to Understand ~ mlplcode
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ mlplunit
AI Tools #7: A Coding Agent Small Enough to Understand ~ MLPL
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ MLPL
Machine Learning #9: Teaching an Array Language to Say CNN ~ MLPL
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ MLPL
Saw #5: Sagas, Languages, and Compiler Chains ~ MLPL
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ MLPL
Array Languages #12: ML Pipelines as X_eTaL Macros ~ MLP
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ MLX backend
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ MLX
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ MLX
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ MLX
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ MMLU benchmark
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ MMSearch
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ MNIST
Small Models (2/6): AI in Your Pocket ~ MobileLLM
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ mockingbird
Made Visible #4: Rosetta M, a Stone with Four Faces ~ mock-up
Five ML Concepts - #24 ~ mode collapse
Five ML Concepts - #27 ~ model editing
How AI Learns Part 4: Memory-Based Learning ~ model editing
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ model evaluation
Five ML Concepts - #22 ~ model steerability
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
Large-Language-Monkeys: Scaling Inference, Not Models
RLM: Recursive Language Models for Massive Context
Small Models (1/6): 976 Parameters Beat Billions
Small Models (2/6): AI in Your Pocket
Small Models (3/6): Planner + Doer = Genius
Small Models (4/6): This AI Has a Visible Brain
Small Models (5/6): Max AI Per Watt
Small Models (6/6): Which Small AI Fits YOUR Laptop?
Saw #12: A Model That Decides, and an Index That Knows
ML Frontier #05: Grokking --- Delayed Generalization ~ modular arithmetic
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ module coupling
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ MoE offload
Saw #11: Building a Tiny Mixture of Experts Microscope ~ moe-microscope
Saw #12: A Model That Decides, and an Index That Knows ~ moe-microscope
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ MoE
Five ML Concepts - #11 ~ MoE
Saw #11: Building a Tiny Mixture of Experts Microscope ~ MoE
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ Mojo Apple GPU
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ mojo build emit shared-lib
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ Mojo C ABI
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ Mojo GPU compilation
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ Mojo GPU programming
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ Mojo Metal CUDA Adreno
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ Mojo Metal
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ Mojo NVIDIA
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ Mojo on Qualcomm Adreno
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
Five ML Concepts - #15 ~ monitoring
Bucket List #2: A Landing Page for Software Tools ~ monitor
midi-cli-rs: Extending with Custom Mood Packs ~ mood packs
midi-cli-rs: Music Generation for AI Coding Agents ~ mood presets
midi-cli-rs: Extending with Custom Mood Packs
Five ML Concepts - #22 ~ more data beats better models
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ mosh
Personal Software #10: A Sudoku That Teaches You the Strategies ~ most constrained cell
music-pipe-rs: Unix Pipelines for MIDI Composition ~ motif
Machine Learning #9: Teaching an Array Language to Say CNN ~ moving average
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ m-poc
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ MSP430
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ MTP
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Solving Sparse Rewards with Many Eyes ~ multi-agent exploration
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ multi-agent orchestration
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ multi-agent orchestration
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ multi-agent orchestration
DyTopo: Dynamic Topology for Multi-Agent AI ~ multi-agent systems
DyTopo: Dynamic Topology for Multi-Agent AI
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Machine Learning #9: Teaching an Array Language to Say CNN ~ multi-axis reduction
Five ML Concepts - #8 ~ multi-head latent attention
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ multi-hop reasoning
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Multi-Hop Reasoning (2/2): The Distribution Trap
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ multi-instrument
music-pipe-rs: Web Demo and Multi-Instrument Arrangements
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ multimodal agents
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ multiplexer
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ multi-token prediction
midi-cli-rs: Extending with Custom Mood Packs ~ music generation
midi-cli-rs: Music Generation for AI Coding Agents ~ music generation
music-pipe-rs: Unix Pipelines for MIDI Composition ~ music generation
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ music-pipe-rs
music-pipe-rs: Unix Pipelines for MIDI Composition
music-pipe-rs: Web Demo and Multi-Instrument Arrangements
midi-cli-rs: Extending with Custom Mood Packs ~ music
midi-cli-rs: Music Generation for AI Coding Agents ~ music
midi-cli-rs: Music Generation for AI Coding Agents
music-pipe-rs: Unix Pipelines for MIDI Composition ~ music
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ music
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ mutual recursion
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ MVP
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ MVS/ESA
TBT #2: Pipelines on OS/390 ~ MVS
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ MXFP4
In-Context Learning Revisited: From Mystery to Engineering
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ Mythical Man-Month
N
Personal Software #10: A Sudoku That Teaches You the Strategies ~ naked pair
Personal Software #10: A Sudoku That Teaches You the Strategies ~ naked single
Machine Learning #9: Teaching an Array Language to Say CNN ~ named axis reduction
Made Visible #4: Rosetta M, a Stone with Four Faces ~ named axis reduction
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ named partial
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ NAND primitive
ML Frontier #05: Grokking --- Delayed Generalization ~ Nanda 2023
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ native extensions
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ native window
Made Visible #1: A Microkernel's Storage, Drawn ~ native3d
Made Visible #2: MesaOS, the Conventional One ~ native3d
Made Visible #3: MLOS, Where Memory Means Something Else ~ native3d
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ native3d
pjmai-rs: Navigation History and Fuzzy Completion ~ navigation history
pjmai-rs: Navigation History and Fuzzy Completion
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ N-body
ML Frontier #01: Neural Collapse ~ NC1
ML Frontier #01: Neural Collapse ~ NC2
ML Frontier #01: Neural Collapse ~ NC3
ML Frontier #01: Neural Collapse ~ NC4
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ n-cpu-moe
JSON et al: A Deep Dive into Data Serialization Formats ~ NDJSON
Saw #12: A Model That Decides, and an Index That Knows ~ Needle
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ negative result
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ Net macro library
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ netlist
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Netronics ELF II 256 bytes
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Energy-Based Learning: From Hopfield Networks to JEPA
Neural-Net-RS: An Educational Neural Network Platform
Five ML Concepts - #29 ~ neural collapse
ML Frontier #01: Neural Collapse ~ neural collapse
Small Models (4/6): This AI Has a Visible Brain ~ neural interpretability
Five ML Concepts - #29 ~ neural network circuits
Five ML Concepts - #28 ~ neural network pruning
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ neural networks
Five ML Concepts - #30: The Journey So Far ~ neural networks
Neural-Net-RS: An Educational Neural Network Platform ~ neural network
Neural-Net-RS: An Educational Neural Network Platform
ML Frontier #01: Neural Collapse
Neural-Net-RS: An Educational Neural Network Platform
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ neurosymbolic AI
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ nextpnr
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ NEXT
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ NN library
Array Languages #17: What Makes a Practical Language, IMHO ~ no ambiguity
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ No Silver Bullet
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ no_std
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ no_std
Saw #12: A Model That Decides, and an Index That Knows ~ non-generative
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ nono sandbox
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ no-op free
Deepseek Papers (1/3): mHC - Training Stability at Any Depth ~ normalization
TBT #11: APL\360 Revisited ~ notation as a tool of thought
Personal Software #10: A Sudoku That Teaches You the Strategies ~ notes
Large-Language-Monkeys: Scaling Inference, Not Models
Saw #12: A Model That Decides, and an Index That Knows ~ Noul
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Saw #11: Building a Tiny Mixture of Experts Microscope ~ NPU
Rabbit-hole #3: FORTH --- Life After Hashing ~ numeric fast path
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ numerical integration in an array language
TBT #11: APL\360 Revisited ~ NumPy
O
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation ~ O(1) lookup
Small Models (3/6): Planner + Doer = Genius ~ o3-mini
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ OBJ export
Cat Finder: Personal Software via Vibe Coding ~ object detection
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ OCaml features
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ OCaml in Pascal
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ OCaml interpreter
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ OCaml
Small Models (2/6): AI in Your Pocket ~ offline AI
Personal Software #10: A Sudoku That Teaches You the Strategies ~ offline
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ Ollama agent
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Ollama
AI Tools #7: A Coding Agent Small Enough to Understand ~ Ollama
ML Frontier #05: Grokking --- Delayed Generalization ~ Omnigrok
ML Frontier #02: In-Context Reinforcement Learning ~ OmniRL
Small Models (5/6): Max AI Per Watt ~ one billion parameters
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ one Mojo kernel three GPUs
Made Visible #2: MesaOS, the Conventional One
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
Cat Finder: Personal Software via Vibe Coding ~ ONNX Runtime
Five ML Concepts - #12 ~ OOD
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ OpenCL C 1.2 kernels
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ OpenCL C driver compile
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ OpenCL deprecated on macOS
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ opencode
AI Tools #7: A Coding Agent Small Enough to Understand ~ OpenCode
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ opencode
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ openFPGALoader
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ operating systems timeline
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ operating systems
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Optane PMem 200
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ optimistic initialization
Five ML Concepts - #26 ~ optimization metrics
Five ML Concepts - #16 ~ optimization
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ Oracle
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ orchestrator
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
AI Tools #7: A Coding Agent Small Enough to Understand ~ org-babel
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ org-babel
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ org-mode babel
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Ornith
TBT #2: Pipelines on OS/390 ~ OS/390
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ oscilloscope
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ OSDev.org
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ outer product
Five ML Concepts - #12 ~ out-of-distribution
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
Five ML Concepts - #16 ~ overconfidence
Five ML Concepts - #3 ~ overfitting
ML Frontier #05: Grokking --- Delayed Generalization ~ overfitting
ML Frontier #01: Neural Collapse ~ overparameterization
P
midi-cli-rs: Extending with Custom Mood Packs
Bucket List #2: A Landing Page for Software Tools
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ PAL language
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ PaperBanana
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
Saw #15: agentrail, Correcting the Record ~ parallel agents
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ parallel development workflow
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ parallel development
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ parallel development
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ parallel development
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ parallel testing
Five ML Concepts - #27 ~ parameter routing
How AI Learns Part 3: Weight-Based Learning ~ Parameter-Efficient Fine-Tuning
How AI Learns Part 6: Toward Continuous Learning ~ Parameter-Efficient Fine-Tuning
How AI Learns Part 7: Designing a Continuous Learning Agent ~ Parameter-Efficient Fine-Tuning
Small Models (1/6): 976 Parameters Beat Billions
JSON et al: A Deep Dive into Data Serialization Formats ~ Parquet
Made Visible #1: A Microkernel's Storage, Drawn ~ parse_json
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ parser animation
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ parser combinators in an array language
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ partition grid
Saw #5: Sagas, Languages, and Compiler Chains ~ Pascal compiler
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ Pascal interpreter
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ Pascal p-code VM
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Pascal
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ Pascal
Large-Language-Monkeys: Scaling Inference, Not Models ~ pass@k
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ patches
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ PCA
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ p-code virtual machine
Bucket List #2: A Landing Page for Software Tools ~ p-code VM
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ p-code VM
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ p-code
How AI Learns Part 3: Weight-Based Learning ~ PEFT
How AI Learns Part 6: Toward Continuous Learning ~ PEFT
How AI Learns Part 7: Designing a Continuous Learning Agent ~ PEFT
Personal Software #10: A Sudoku That Teaches You the Strategies ~ pencil marks
Five ML Concepts - #5 ~ perceptron
AI Tools #7: A Coding Agent Small Enough to Understand ~ permissions allow ask deny
Five ML Concepts - #15 ~ perplexity
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ personal software
Cat Finder: Personal Software via Vibe Coding ~ personal software
Neural-Net-RS: An Educational Neural Network Platform ~ personal software
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ personal software
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ Personal Software
Cat Finder: Personal Software via Vibe Coding
Personal Software #10: A Sudoku That Teaches You the Strategies
Personal Software #11: A Campus for the Public Work
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ per-user sandboxing
Small Models (5/6): Max AI Per Watt
ML Frontier #05: Grokking --- Delayed Generalization ~ phase transition
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ Phi-2
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ phoenix
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
TBT #3: Vector Graphics Games ~ phosphor
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ photo lab
Made Visible #2: MesaOS, the Conventional One ~ physical memory manager
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ Pi agent
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Pi agent
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way ~ pi web search
Made Visible #1: A Microkernel's Storage, Drawn ~ picking
Array Languages #12: ML Pipelines as X_eTaL Macros ~ pipe operator in an array language
Five ML Concepts - #28 ~ pipeline parallelism
Array Languages #12: ML Pipelines as X_eTaL Macros
TBT #2: Pipelines on OS/390
music-pipe-rs: Unix Pipelines for MIDI Composition
Saw #1: pjmai-rs, Rig, and langchain-rust ~ pjmai-rs
Saw #1: pjmai-rs, Rig, and langchain-rust
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ pjmai-rs
TBT #6: PJMAI-RS - A Shell That Knows Your Projects
pjmai-rs: Navigation History and Fuzzy Completion
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ pjmai
pjmai-rs: Navigation History and Fuzzy Completion ~ pjmai
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ PL/EDIT
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ PL/EDIT
Saw #5: Sagas, Languages, and Compiler Chains ~ PL/I
Bucket List #2: A Landing Page for Software Tools ~ PL/SW
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ PL/SW
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ PL/SW
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ PL/SW
Saw #5: Sagas, Languages, and Compiler Chains ~ PL/SW
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ PL/SW
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ PL/SW
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ PL/SW
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ PL/X
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ PL/X
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ plan execute review
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ planner executor reviewer
Small Models (3/6): Planner + Doer = Genius ~ planner-doer architecture
Small Models (3/6): Planner + Doer = Genius
Five ML Concepts - #21 ~ planning vs prediction
Neural-Net-RS: An Educational Neural Network Platform
MCP: Teaching Claude to Play (and Trash Talk)
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
midi-cli-rs: Extending with Custom Mood Packs ~ plugins
Small Models (2/6): AI in Your Pocket
Personal Software #10: A Sudoku That Teaches You the Strategies ~ point symmetry
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ pointer rewriting
Personal Software #10: A Sudoku That Teaches You the Strategies ~ pointing
TBT #3: Vector Graphics Games ~ Pong
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
Five ML Concepts - #6 ~ positional encoding
ML Frontier #05: Grokking --- Delayed Generalization ~ Power 2022
Large-Language-Monkeys: Scaling Inference, Not Models ~ power law
Array Languages #17: What Makes a Practical Language, IMHO ~ practical language
Array Languages #17: What Makes a Practical Language, IMHO
Five ML Concepts - #12 ~ precision
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ preemptive multitasking
Five ML Concepts - #18 ~ preference learning
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ pre-push hook
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ pressure sensor
Five ML Concepts - #5 ~ pre-training
How AI Learns Part 1: The Many Meanings of Learning ~ pretraining
How AI Learns Part 3: Weight-Based Learning ~ pretraining
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ primitive set
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ Princeton
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ printer
Cat Finder: Personal Software via Vibe Coding ~ privacy-first
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ procedural 3D scenes
Bucket List #1: Things I've Always Wanted to Build ~ procedural audio
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ procedural macros
Five ML Concepts - #21 ~ production rollbacks
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ productivity tools
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ PROFILE-ON
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ program manager
TBT #4: ToonTalk - Teaching Robots to Program ~ programming by demonstration
Array Languages #17: What Makes a Practical Language, IMHO ~ programming language design philosophy
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ programming languages timeline
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ programming languages
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
TBT #1: My First Program Was a Horse Race
TBT #4: ToonTalk - Teaching Robots to Program
ML Frontier #05: Grokking --- Delayed Generalization ~ progress measures
Personal Software #10: A Sudoku That Teaches You the Strategies ~ progressive web app
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ project compartmentalization
Personal Software #11: A Campus for the Public Work ~ project discoverability
Saw #1: pjmai-rs, Rig, and langchain-rust ~ project management
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ project manager
pjmai-rs: Navigation History and Fuzzy Completion ~ project manager
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ project switching
pjmai-rs: Navigation History and Fuzzy Completion ~ project switching
TBT #6: PJMAI-RS - A Shell That Knows Your Projects
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ Prolog in Rust
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Five ML Concepts - #6 ~ prompt engineering
Five ML Concepts - #21 ~ prompt injection
ML Frontier #02: In-Context Reinforcement Learning ~ prompt-based RL
Five ML Concepts - #6 ~ prompting
ML Frontier #04: Is Chain of Thought Real? ~ prompting
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Made Visible #4: Rosetta M, a Stone with Four Faces ~ proposed notation
JSON et al: A Deep Dive into Data Serialization Formats ~ Protobuf
JSON et al: A Deep Dive into Data Serialization Formats ~ Protocol Buffers
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ proto-forth-wasm
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
Saw #15: agentrail, Correcting the Record ~ provenance
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ PTX ptxas CUDA driver
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ PTX walkthrough
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ PTY management
Personal Software #11: A Campus for the Public Work ~ public work index
Personal Software #11: A Campus for the Public Work
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ punch cards
Personal Software #10: A Sudoku That Teaches You the Strategies ~ puzzle generator
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ pvm
Personal Software #10: A Sudoku That Teaches You the Strategies ~ PWA
Small Models (5/6): Max AI Per Watt ~ Pythia
Q
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Q4_K_M
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ QEMU
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ Q-learning
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ quad system variables
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ quadrature
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Quadro K4200
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
rank-wav: Ranking Audio Files by Acoustic Quality
Five ML Concepts - #9 ~ quantization
AI Tools #7: A Coding Agent Small Enough to Understand ~ qwen2.5-coder
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Qwen3.5
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Qwen3.6
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Qwen3.8
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Qwen3-Coder
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Qwen3
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Qwen
R
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
Rabbit-hole #3: FORTH --- Life After Hashing
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
TBT #1: My First Program Was a Horse Race
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ Racket gcd
Five ML Concepts - #30: The Journey So Far ~ RAG
Five ML Concepts - #10 ~ RAG
How AI Learns Part 1: The Many Meanings of Learning ~ RAG
How AI Learns Part 4: Memory-Based Learning ~ RAG
How AI Learns Part 7: Designing a Continuous Learning Agent ~ RAG
Saw #1: pjmai-rs, Rig, and langchain-rust ~ RAG
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ RAM price history
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Random
rank-wav: Ranking Audio Files by Acoustic Quality
rank-wav: Ranking Audio Files by Acoustic Quality ~ rank-wav
rank-wav: Ranking Audio Files by Acoustic Quality
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ Raspberry Pi RAM
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ Raspberry Pi
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ ratchet
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
Array Languages #12: ML Pipelines as X_eTaL Macros ~ raw strings
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ ray march
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ reaction-diffusion
Array Languages #17: What Makes a Practical Language, IMHO ~ readability
Array Languages #1: X_eTaL, an Array Language You Can Read
ML Frontier #04: Is Chain of Thought Real?
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ reasoning-from-scratch
How AI Learns Part 5: Context Engineering & Recursive Reasoning
ML Frontier #04: Is Chain of Thought Real? ~ reasoning
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Multi-Hop Reasoning (2/2): The Distribution Trap
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
Five ML Concepts - #12 ~ recall
Rabbit-hole #3: FORTH --- Life After Hashing ~ recent-hit cache
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ reclaim
TBT #2: Pipelines on OS/390 ~ record-at-a-time
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ records and choices
Saw #15: agentrail, Correcting the Record
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ recovery
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
Five ML Concepts - #11 ~ recurrent neural network
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ recursion without a name
Small Models (1/6): 976 Parameters Beat Billions ~ recursive depth
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ recursive language models
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ recursive language models
How AI Learns Part 6: Toward Continuous Learning ~ Recursive Language Models
How AI Learns Part 7: Designing a Continuous Learning Agent ~ Recursive Language Models
RLM: Recursive Language Models for Massive Context ~ recursive language models
Saw #11: Building a Tiny Mixture of Experts Microscope ~ recursive reasoning
How AI Learns Part 5: Context Engineering & Recursive Reasoning
RLM: Recursive Language Models for Massive Context
Machine Learning #9: Teaching an Array Language to Say CNN ~ reduce
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ reduction tree
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ reduction
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ reference implementation
ML Frontier #02: In-Context Reinforcement Learning ~ reflexion
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ register allocation
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ regression testing
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ regression testing
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ regression tests
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ regress
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ reg-rs
Saw #2: reg-rs, avoid-compaction, and agentrail-rs
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ reg-rs
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ reg-rs
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
Five ML Concepts - #6 ~ regularization
ML Frontier #05: Grokking --- Delayed Generalization ~ regularization
Five ML Concepts - #9 ~ reinforcement learning from human feedback
How AI Learns Part 3: Weight-Based Learning ~ Reinforcement Learning from Human Feedback
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ reinforcement learning
ML Frontier #04: Is Chain of Thought Real? ~ reinforcement learning
ML Frontier #02: In-Context Reinforcement Learning
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
Five ML Concepts - #22 ~ Rejection Sampling Fine-Tuning
Multi-Hop Reasoning (2/2): The Distribution Trap ~ rejection sampling
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ relocation
Five ML Concepts - #4 ~ ReLU
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ reopen
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ reorder
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
Large-Language-Monkeys: Scaling Inference, Not Models ~ repeated sampling
Five ML Concepts - #27 ~ replay buffers
How AI Learns Part 6: Toward Continuous Learning ~ replay
Five ML Concepts - #25 ~ representation learning
ML Frontier #01: Neural Collapse ~ representation learning
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ reserved heap
Saw #15: agentrail, Correcting the Record ~ reserve
Made Visible #3: MLOS, Where Memory Means Something Else ~ residency
Made Visible #3: MLOS, Where Memory Means Something Else ~ resident model state
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ resident process
Array Languages #12: ML Pipelines as X_eTaL Macros ~ residual connection
ML Frontier #01: Neural Collapse ~ ResNets
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ retargetable code generation
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ retired CUDA cards
Bucket List #1: Things I've Always Wanted to Build ~ retirement projects
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ retirement projects
Five ML Concepts - #10 ~ retrieval-augmented generation
How AI Learns Part 1: The Many Meanings of Learning ~ Retrieval-Augmented Generation
How AI Learns Part 4: Memory-Based Learning ~ Retrieval-Augmented Generation
How AI Learns Part 7: Designing a Continuous Learning Agent ~ Retrieval-Augmented Generation
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ retro computing
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ retro computing
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ retro tooling
Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
In-Context Learning Revisited: From Mystery to Engineering
TBT #11: APL\360 Revisited
Five ML Concepts - #24 ~ reward hacking
Five ML Concepts - #30: The Journey So Far ~ reward hacking
Large-Language-Monkeys: Scaling Inference, Not Models ~ reward models
ML Frontier #02: In-Context Reinforcement Learning ~ reward-based learning
Many-Eyes Learning: Intrinsic Rewards and Diversity
Solving Sparse Rewards with Many Eyes
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ Rich Hickey
ML Frontier #05: Grokking --- Delayed Generalization ~ rich training
Saw #1: pjmai-rs, Rig, and langchain-rust ~ rig framework
Saw #1: pjmai-rs, Rig, and langchain-rust
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ Ring 3
Made Visible #2: MesaOS, the Conventional One ~ Ring 3
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ RISC architecture
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ RISC
ML Frontier #02: In-Context Reinforcement Learning ~ RL without training
Five ML Concepts - #9 ~ RLHF
How AI Learns Part 3: Weight-Based Learning ~ RLHF
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ RLM
How AI Learns Part 6: Toward Continuous Learning ~ RLM
How AI Learns Part 7: Designing a Continuous Learning Agent ~ RLM
RLM: Recursive Language Models for Massive Context ~ RLM
RLM: Recursive Language Models for Massive Context
Five ML Concepts - #11 ~ RNN
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ Robot Chase
TBT #4: ToonTalk - Teaching Robots to Program
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ ROCm HIP AMDGCN
Five ML Concepts - #14 ~ ROC
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ Rodrigues formula
Five ML Concepts - #6 ~ RoPE
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ Rosetta M
Made Visible #4: Rosetta M, a Stone with Four Faces ~ Rosetta M
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Rosetta M
Made Visible #4: Rosetta M, a Stone with Four Faces ~ Rosetta Stone
Made Visible #4: Rosetta M, a Stone with Four Faces
Five ML Concepts - #6 ~ rotary positional embeddings
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ rotate
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ rotation matrices
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ RS/6000 1GB
Five ML Concepts - #22 ~ RSFT
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs ~ RSFT
Multi-Hop Reasoning (2/2): The Distribution Trap ~ RSFT
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ RTX 3060 Laptop GPU
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ RTX 3060
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ RTX 3060
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ RTX 3090
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ RTX 3090
Lucy 20%: Upgrading My Home AI Cluster ~ RTX 3090
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ RTX 4070 Laptop GPU
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ RTX 5060 Ti
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ RTX 5060 Ti
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ RTX 5060 Ti
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ Rubik's cube solver
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
Array Languages #6: X_eTaL-games, Rules That Are Arrays
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ runtime image
Saw #1: pjmai-rs, Rig, and langchain-rust ~ rust 2024 edition
Saw #1: pjmai-rs, Rig, and langchain-rust ~ rust ai
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ Rust CLI
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ Rust CLI
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ Rust CLI
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ Rust CLI
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ Rust CLI
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ Rust CLI
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Rust CLI
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ rust cli
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ Rust CLI
pjmai-rs: Navigation History and Fuzzy Completion ~ rust cli
rank-wav: Ranking Audio Files by Acoustic Quality ~ Rust CLI
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ Rust harness
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ Rust macros lints diagnostics
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ Rust no_std
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ Rust shared library
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ rusticl OpenCL
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
Array Languages #1: X_eTaL, an Array Language You Can Read ~ Rust
Bucket List #1: Things I've Always Wanted to Build ~ Rust
Cat Finder: Personal Software via Vibe Coding ~ Rust
DyTopo: Dynamic Topology for Multi-Agent AI ~ Rust
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ Rust
Neural-Net-RS: An Educational Neural Network Platform ~ Rust
Personal Software #10: A Sudoku That Teaches You the Strategies ~ Rust
Personal Software #11: A Campus for the Public Work ~ Rust
RLM: Recursive Language Models for Massive Context ~ Rust
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ Rust
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ Rust
TBT #2: Pipelines on OS/390 ~ Rust
TBT #3: Vector Graphics Games ~ Rust
TBT #4: ToonTalk - Teaching Robots to Program ~ Rust
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ Rust
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ Rust
TBT #11: APL\360 Revisited ~ Rust
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ Rust
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ Rust
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ Rust
midi-cli-rs: Extending with Custom Mood Packs ~ Rust
midi-cli-rs: Music Generation for AI Coding Agents ~ Rust
music-pipe-rs: Unix Pipelines for MIDI Composition ~ Rust
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ RV32I
S
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ S' combinator
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ Safetensors
How AI Learns Part 7: Designing a Continuous Learning Agent ~ safety
Saw #5: Sagas, Languages, and Compiler Chains ~ saga archiving
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ saga workflow
Saw #5: Sagas, Languages, and Compiler Chains
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ saga
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ saga
Saw #15: agentrail, Correcting the Record ~ saga
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ Sage bird
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ Sage
Five ML Concepts - #29 ~ SAM
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
AI Tools #7: A Coding Agent Small Enough to Understand ~ sandbox
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ SAVE-IMAGE
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Saw #11: Building a Tiny Mixture of Experts Microscope
Saw #12: A Model That Decides, and an Index That Knows
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
Saw #15: agentrail, Correcting the Record
Saw #1: pjmai-rs, Rig, and langchain-rust
Saw #2: reg-rs, avoid-compaction, and agentrail-rs
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Saw #5: Sagas, Languages, and Compiler Chains
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
Machine Learning #9: Teaching an Array Language to Say CNN
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs ~ scaffolded training
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Saw #12: A Model That Decides, and an Index That Knows ~ Scale
music-pipe-rs: Unix Pipelines for MIDI Composition ~ scale
Five ML Concepts - #30: The Journey So Far ~ scaling laws
Five ML Concepts - #17 ~ scaling laws
Large-Language-Monkeys: Scaling Inference, Not Models
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ scan
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ scenario A B C D E
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ schema v1.2
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ scout diversity
Solving Sparse Rewards with Many Eyes ~ scout-based learning
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ SDL3 GPU
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop ~ Seatbelt
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Personal Software #10: A Sudoku That Teaches You the Strategies ~ seeded generation
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ segments
TBT #1: My First Program Was a Horse Race ~ Selectric typeball
TBT #11: APL\360 Revisited ~ Selectric typeball
Energy-Based Learning: From Hopfield Networks to JEPA ~ self supervised learning
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ self-application
Five ML Concepts - #7 ~ self-attention
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ self-hosted compiler
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ self-hosting assembler
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ self-play
Five ML Concepts - #29 ~ self-training instability
DyTopo: Dynamic Topology for Multi-Agent AI ~ semantic routing
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ sensor array
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ seq command
ML Frontier #02: In-Context Reinforcement Learning ~ sequence modeling
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ Serial Parameter Machine
JSON et al: A Deep Dive into Data Serialization Formats
Saw #12: A Model That Decides, and an Index That Knows ~ SetFit
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Sets
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
How AI Learns Part 3: Weight-Based Learning ~ SFT
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ SHA-256
Five ML Concepts - #17 ~ shadow deployment
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ shadowed words
Small Models (1/6): 976 Parameters Beat Billions ~ Shakespeare training
Array Languages #14: Types, Lints and Errors in X_eTaL ~ shape checks
Array Languages #12: ML Pipelines as X_eTaL Macros ~ shape contracts
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ Share algorithm
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ Share algorithm
Many-Eyes Learning: Intrinsic Rewards and Diversity ~ shared Q-table
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24
How AI Learns Part 6: Toward Continuous Learning ~ Share
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ sharing language snippets
Saw #1: pjmai-rs, Rig, and langchain-rust ~ sharpen the saw
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ sharpen the saw
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ Sharpen the Saw
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ Sharpen the Saw
Saw #15: agentrail, Correcting the Record ~ Sharpen the Saw
Five ML Concepts - #29 ~ sharpness-aware minimization
TBT #6: PJMAI-RS - A Shell That Knows Your Projects ~ shell integration
pjmai-rs: Navigation History and Fuzzy Completion ~ shell integration
Bucket List #2: A Landing Page for Software Tools ~ shell
TBT #6: PJMAI-RS - A Shell That Knows Your Projects
Five ML Concepts - #13 ~ shortcut learning
Made Visible #4: Rosetta M, a Stone with Four Faces ~ side by side
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ sidecar files
Five ML Concepts - #4 ~ sigmoid
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ significant whitespace
Array Languages #14: Types, Lints and Errors in X_eTaL ~ silent wrong answers
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ silent wrong answers
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ Simple Made Easy
ML Frontier #01: Neural Collapse ~ simplex ETF
ML Frontier #01: Neural Collapse ~ simplex geometry
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ Singular Value Decomposition
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Sipeed Tang Nano
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ Sipeed Tang Nano
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ six rotations
TBT #11: APL\360 Revisited ~ six-space prompt
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ skill library
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ skills
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Machine Learning #9: Teaching an Array Language to Say CNN ~ sliding window
Array Languages #17: What Makes a Practical Language, IMHO ~ small language core
Small Models (4/6): This AI Has a Visible Brain ~ small language models
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ small language models
ML Frontier #05: Grokking --- Delayed Generalization ~ small networks
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
AI Tools #7: A Coding Agent Small Enough to Understand
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Small Models (6/6): Which Small AI Fits YOUR Laptop?
Small Models (1/6): 976 Parameters Beat Billions
Small Models (2/6): AI in Your Pocket
Small Models (3/6): Planner + Doer = Genius
Small Models (4/6): This AI Has a Visible Brain
Small Models (5/6): Max AI Per Watt
Small Models (6/6): Which Small AI Fits YOUR Laptop?
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs ~ SmolLM-135M
Multi-Hop Reasoning (2/2): The Distribution Trap ~ SmolLM-360M
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ SmolLM
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ Smullyan
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ Smullyan
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ snapshot testing
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover ~ snapshot
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ SNOBOL4
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ SNOBOL4
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ SNOBOL4
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ social preview cards
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ soft CPU
Five ML Concepts - #25 ~ soft labels
Five ML Concepts - #11 ~ softmax
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ software engineering career timeline
Bucket List #2: A Landing Page for Software Tools ~ software tools
Personal Software #11: A Campus for the Public Work ~ Software Wrighter Research Campus
Bucket List #2: A Landing Page for Software Tools
Cat Finder: Personal Software via Vibe Coding
Personal Software #10: A Sudoku That Teaches You the Strategies
Personal Software #11: A Campus for the Public Work
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Welcome to Software Wrighter Lab
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
Solving Sparse Rewards with Many Eyes
Made Visible #3: MLOS, Where Memory Means Something Else
rank-wav: Ranking Audio Files by Acoustic Quality ~ sound quality
midi-cli-rs: Music Generation for AI Coding Agents ~ SoundFont
midi-cli-rs: Extending with Custom Mood Packs ~ sound
midi-cli-rs: Music Generation for AI Coding Agents ~ sound
music-pipe-rs: Unix Pipelines for MIDI Composition ~ sound
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ sound
Rabbit-hole #3: FORTH --- Life After Hashing ~ source lookup count
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ source-to-source macros
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ SP@
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ space versus time
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ spans
Small Models (4/6): This AI Has a Visible Brain ~ sparse activations
Five ML Concepts - #28 ~ sparse activation
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers ~ sparse attention
Small Models (4/6): This AI Has a Visible Brain ~ sparse coding
DyTopo: Dynamic Topology for Multi-Agent AI ~ sparse graphs
Solving Sparse Rewards with Many Eyes ~ sparse rewards
Saw #11: Building a Tiny Mixture of Experts Microscope ~ sparse routing
Solving Sparse Rewards with Many Eyes
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
rank-wav: Ranking Audio Files by Acoustic Quality ~ spectral analysis
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
Five ML Concepts - #5 ~ speculative decoding
Small Models (5/6): Max AI Per Watt ~ speculative decoding
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ SPI emulator
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ SPIR-V retarget NVPTX
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ SPI
Personal Software #10: A Sudoku That Teaches You the Strategies ~ SplitMix64
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ SPM
Five ML Concepts - #14 ~ spurious correlations
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ SQLite
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ SQLite
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ SQLite
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ SQLite
How AI Learns Part 2: Catastrophic Forgetting vs Context Rot ~ stability plasticity tradeoff
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Array Languages #12: ML Pipelines as X_eTaL Macros ~ stable softmax
Personal Software #11: A Campus for the Public Work ~ stable URLs
Small Models (5/6): Max AI Per Watt ~ StableLM
pjmai-rs: Navigation History and Fuzzy Completion ~ stack management
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ staged optimization
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ Star Trek BASIC
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
Array Languages #17: What Makes a Practical Language, IMHO ~ static typing
Array Languages #1: X_eTaL, an Array Language You Can Read ~ statically typed array language
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ status dashboard
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ Steffen Smolka
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ stencil macros
Machine Learning #9: Teaching an Array Language to Say CNN ~ stencil
ML Frontier #04: Is Chain of Thought Real? ~ step-by-step reasoning
Made Visible #4: Rosetta M, a Stone with Four Faces
Made Visible #1: A Microkernel's Storage, Drawn ~ storage layout
Made Visible #1: A Microkernel's Storage, Drawn
Saw #15: agentrail, Correcting the Record ~ stranded steps
Personal Software #10: A Sudoku That Teaches You the Strategies
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ streaming weights
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ strict evaluation
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ strict JSON
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ Strings
Made Visible #1: A Microkernel's Storage, Drawn ~ struct of arrays
Saw #2: reg-rs, avoid-compaction, and agentrail-rs ~ structured handoffs
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ structured knowledge
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ structured workflow
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
pjmai-rs: Navigation History and Fuzzy Completion ~ subdirectory navigation
Array Languages #1: X_eTaL, an Array Language You Can Read ~ subscript axis
How AI Learns Part 6: Toward Continuous Learning ~ subspace regularization
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ Sudoku
Personal Software #10: A Sudoku That Teaches You the Strategies ~ Sudoku
Personal Software #10: A Sudoku That Teaches You the Strategies
Array Languages #11: Math Equations as X_eTaL Macros ~ sum notation
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ Sun Microsystems
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Five ML Concepts - #4 ~ superposition
Array Languages #1: X_eTaL, an Array Language You Can Read ~ superscript namespace
How AI Learns Part 3: Weight-Based Learning ~ Supervised Fine-Tuning
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ supervised fine-tuning
midi-cli-rs: Music Generation for AI Coding Agents ~ suspense
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ SVD
Lucy 20%: Upgrading My Home AI Cluster ~ SVD
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ SVD
Towards Continuous LLM Learning (2): Routing Prevents Forgetting ~ SVD
Personal Software #11: A Campus for the Public Work ~ SVG
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ SVG
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ sw-apl-workspaces
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-apl-workspaces
Array Languages #1: X_eTaL, an Array Language You Can Read ~ sw-apl
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ sw-apl
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-apl
TBT #11: APL\360 Revisited ~ sw-apl
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ sw-apl
Saw #12: A Model That Decides, and an Index That Knows ~ sw-atlas
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-atlas
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ sw-checklist
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ sw-cor24-forth
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ sw-cor24-forth
Rabbit-hole #3: FORTH --- Life After Hashing ~ sw-cor24-forth
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ sw-cor24-forth
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ sw-cor24-pascal
Large-Language-Monkeys: Scaling Inference, Not Models ~ SWE-bench
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ sw-embed
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ sw-embed
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ sw-launcher
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ sw-launch
AI Tools #7: A Coding Agent Small Enough to Understand ~ sw-MLPL
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ sw-MLPL
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ sw-MLPL
Machine Learning #9: Teaching an Array Language to Say CNN ~ sw-MLPL
Made Visible #1: A Microkernel's Storage, Drawn ~ sw-MLPL
Made Visible #2: MesaOS, the Conventional One ~ sw-MLPL
Made Visible #3: MLOS, Where Memory Means Something Else ~ sw-MLPL
Made Visible #4: Rosetta M, a Stone with Four Faces ~ sw-MLPL
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ sw-MLPL
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ sw-MLPL
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ sw-MLPL
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ sw-MLPL
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
Saw #11: Building a Tiny Mixture of Experts Microscope ~ sw-MLPL
Saw #12: A Model That Decides, and an Index That Knows ~ sw-MLPL
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-MLPL
TBT #11: APL\360 Revisited ~ sw-MLPL
Personal Software #10: A Sudoku That Teaches You the Strategies ~ swordfish
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ sw-os-ml
Made Visible #3: MLOS, Where Memory Means Something Else ~ sw-os-ml
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-os-ml
Bucket List #2: A Landing Page for Software Tools ~ SWS
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ SWS
Bucket List #4: Three Operating Systems and an ML Hardware Emulator ~ SWTOS
Made Visible #1: A Microkernel's Storage, Drawn ~ SWTOS
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ sw-tos
Small Models (6/6): Which Small AI Fits YOUR Laptop? ~ synthetic training data
midi-cli-rs: Extending with Custom Mood Packs ~ synthwave
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ system emulator
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ system functions
Saw #12: A Model That Decides, and an Index That Knows ~ System One model
Five ML Concepts - #22 ~ system reliability
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ System/360
Welcome to Software Wrighter Lab ~ systems programming
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
T
pjmai-rs: Navigation History and Fuzzy Completion ~ tab completion
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ tacit programming
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ Tags macro library
MCP: Teaching Claude to Play (and Trash Talk)
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Tang Primer
AI Tools #7: A Coding Agent Small Enough to Understand ~ tangle
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ TBT
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
TBT #11: APL\360 Revisited
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
TBT #1: My First Program Was a Horse Race
TBT #2: Pipelines on OS/390
TBT #3: Vector Graphics Games
TBT #4: ToonTalk - Teaching Robots to Program
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
TBT #6: PJMAI-RS - A Shell That Knows Your Projects
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept ~ TCA9548A
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ TDD
Personal Software #10: A Sudoku That Teaches You the Strategies ~ TDD
Saw #12: A Model That Decides, and an Index That Knows ~ TDM
Personal Software #10: A Sudoku That Teaches You the Strategies
MCP: Teaching Claude to Play (and Trash Talk)
Machine Learning #9: Teaching an Array Language to Say CNN
TBT #4: ToonTalk - Teaching Robots to Program
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ tech debt
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ teletype Red Alert bell
Five ML Concepts - #2 ~ temperature sampling
TBT #3: Vector Graphics Games ~ Tempest
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ template editor
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ template-driven editing
ML Frontier #02: In-Context Reinforcement Learning ~ temporal difference learning
Five ML Concepts - #28 ~ tensor parallelism
ML Frontier #01: Neural Collapse ~ terminal phase training
Bucket List #1: Things I've Always Wanted to Build ~ ternary computer
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Tesla M10
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Tesla M40
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Tesla P100
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Tesla P4
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust ~ test automation
TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ text adventure
Lucy 20%: Upgrading My Home AI Cluster ~ text-to-image
Lucy 20%: Upgrading My Home AI Cluster ~ text-to-video
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
Small Models (2/6): AI in Your Pocket ~ therapist chatbot
Bucket List #1: Things I've Always Wanted to Build
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
ML Frontier #04: Is Chain of Thought Real?
Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum ~ threaded code
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ three optimization layers
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ three-layer architecture
Bucket List #4: Three Operating Systems and an ML Hardware Emulator
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Five ML Concepts - #12 ~ throughput
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ Throwback Thursday
MCP: Teaching Claude to Play (and Trash Talk) ~ tic-tac-toe
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ tic-tac-toe
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ TiddlyWiki
Made Visible #3: MLOS, Where Memory Means Something Else ~ tiering
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ TiKi
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ time-sharing BASIC
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ time-sharing
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ Tiny CNN
Saw #11: Building a Tiny Mixture of Experts Microscope ~ tiny LLM
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ tinyc
Small Models (5/6): Max AI Per Watt ~ TinyLlama
Saw #11: Building a Tiny Mixture of Experts Microscope
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ TMP101 simulator
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ TMS1000
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ tmux
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ to mock a mockingbird
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ To Mock a Mockingbird
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ TodoMVC
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ TodoMVC
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
Five ML Concepts - #3 ~ tokenization
JSON et al: A Deep Dive into Data Serialization Formats ~ TOML
midi-cli-rs: Extending with Custom Mood Packs ~ TOML
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ tool calling
AI Tools #7: A Coding Agent Small Enough to Understand ~ tool dispatch
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ tool use
Five ML Concepts - #23 ~ tool use
How AI Learns Part 5: Context Engineering & Recursive Reasoning ~ tool use
ML Frontier #04: Is Chain of Thought Real? ~ tool use
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ tools I have used
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
AI Tools #7: A Coding Agent Small Enough to Understand
Bucket List #2: A Landing Page for Software Tools
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools
TBT #4: ToonTalk - Teaching Robots to Program ~ ToonTalk
TBT #4: ToonTalk - Teaching Robots to Program
JSON et al: A Deep Dive into Data Serialization Formats ~ TOON
Saw #11: Building a Tiny Mixture of Experts Microscope ~ top-1 routing
Saw #11: Building a Tiny Mixture of Experts Microscope ~ top-2 routing
Rabbit-hole #3: FORTH --- Life After Hashing ~ top-K cache
DyTopo: Dynamic Topology for Multi-Agent AI
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ total parsing
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Towards Continuous LLM Learning (2): Routing Prevents Forgetting
How AI Learns Part 6: Toward Continuous Learning
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Tower of Hanoi without recursion
Machine Learning #9: Teaching an Array Language to Say CNN ~ trailing-axis broadcasting
Five ML Concepts - #16 ~ train validation test split
Machine Learning #9: Teaching an Array Language to Say CNN ~ trainable convolution
Five ML Concepts - #24 ~ training contamination
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ training in the browser
Made Visible #4: Rosetta M, a Stone with Four Faces ~ training loss
Deepseek Papers (1/3): mHC - Training Stability at Any Depth ~ training stability
Five ML Concepts - #26 ~ training transformations
Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ trains fork atop
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ trains
ML Frontier #02: In-Context Reinforcement Learning ~ trajectory examples
Five ML Concepts - #4 ~ transfer learning
Five ML Concepts - #1 ~ transformer architecture
Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
In-Context Learning Revisited: From Mystery to Engineering ~ transformers
ML Frontier #01: Neural Collapse ~ transformers
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ trapezoid rule
Multi-Hop Reasoning (2/2): The Distribution Trap
MCP: Teaching Claude to Play (and Trash Talk) ~ trash talk
MCP: Teaching Claude to Play (and Trash Talk)
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ tree reduction
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ triangle function
Made Visible #4: Rosetta M, a Stone with Four Faces ~ triple sum
Saw #11: Building a Tiny Mixture of Experts Microscope ~ TRM
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars ~ TRS-80 Expansion Interface 48K
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ TRS-80 magazine listing
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ TRS-80
TBT #2: Pipelines on OS/390 ~ TSO Pipelines
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ TSO
TBT #4: ToonTalk - Teaching Robots to Program ~ tt-rs
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ TTTML
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ TTTML
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ tuples
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ tuples
Saw #9: Espanso, Kate, ShareX, and Pluggable I2C Devices on COR24 ~ Tuplet glyphs
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ Tuplet language
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ Tuplet language
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ Tuplet
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ Turing
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ two-host portability
Saw #12: A Model That Decides, and an Index That Knows ~ typed decision model
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ typed decision model
Saw #12: A Model That Decides, and an Index That Knows ~ typed decision
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ typed facade
Saw #1: pjmai-rs, Rig, and langchain-rust ~ type-safe agents
Saw #12: A Model That Decides, and an Index That Knows ~ TypeSafe AI
Array Languages #14: Types, Lints and Errors in X_eTaL
Array Languages #1: X_eTaL, an Array Language You Can Read ~ typographic decoration
U
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ u_se macro
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ UART
Five ML Concepts - #20 ~ uncertainty estimation
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ unconsumed input error
Array Languages #1: X_eTaL, an Array Language You Can Read ~ underline function
AI Tools #7: A Coding Agent Small Enough to Understand
Personal Software #10: A Sudoku That Teaches You the Strategies ~ uniqueness
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC ~ UNIVAC 1108 Star Trek BASIC
TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
Five ML Concepts - #13 ~ universal approximation theorem
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ Unix pipes in an array language
music-pipe-rs: Unix Pipelines for MIDI Composition ~ Unix pipes
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ Unix pipes
music-pipe-rs: Unix Pipelines for MIDI Composition
Saw #15: agentrail, Correcting the Record ~ unreserve
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ unresolved symbols
Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator ~ unsupported target
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
Lucy 20%: Upgrading My Home AI Cluster
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ user-defined macros
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails ~ UWSH
V
Five ML Concepts - #20 ~ VAE
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ validator
Deepseek Papers (1/3): mHC - Training Stability at Any Depth ~ vanishing gradients
Five ML Concepts - #20 ~ variational autoencoders
How AI Learns Part 4: Memory-Based Learning ~ vector database
TBT #3: Vector Graphics Games ~ vector graphics
Saw #1: pjmai-rs, Rig, and langchain-rust ~ vector store
TBT #3: Vector Graphics Games
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A ~ vendor lockfile
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ vendoring
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
Large-Language-Monkeys: Scaling Inference, Not Models ~ verification
AI Tools #7: A Coding Agent Small Enough to Understand ~ verify gate
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Verilog-2005 emitter
TBT #13: Many Decades of Learning the Next Thing --- Timelines of the Tools ~ version control timeline
Cat Finder: Personal Software via Vibe Coding
Bucket List #1: Things I've Always Wanted to Build ~ vibe coding
Bucket List #2: A Landing Page for Software Tools ~ vibe coding
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ vibe coding
Cat Finder: Personal Software via Vibe Coding ~ vibe coding
Neural-Net-RS: An Educational Neural Network Platform ~ vibe coding
Personal Software #10: A Sudoku That Teaches You the Strategies ~ vibe coding
Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL ~ vibe coding
TBT #2: Pipelines on OS/390 ~ vibe coding
midi-cli-rs: Music Generation for AI Coding Agents ~ vibe coding
AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet ~ vibe-coding
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ vibe-coding
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ vibe-maintenance
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Cat Finder: Personal Software via Vibe Coding
Made Visible #2: MesaOS, the Conventional One ~ virtual memory manager
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ visible compilers
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers
Made Visible #1: A Microkernel's Storage, Drawn
Made Visible #2: MesaOS, the Conventional One
Made Visible #3: MLOS, Where Memory Means Something Else
Made Visible #4: Rosetta M, a Stone with Four Faces
Small Models (4/6): This AI Has a Visible Brain
Five ML Concepts - #4 ~ vision-language models
Made Visible #4: Rosetta M, a Stone with Four Faces ~ visual programming language
TBT #4: ToonTalk - Teaching Robots to Program ~ visual programming
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ VisualToolBench
Energy-Based Learning: From Hopfield Networks to JEPA ~ V-JEPA
Five ML Concepts - #4 ~ VLM
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Lucy 20%: Upgrading My Home AI Cluster ~ voice cloning
Lucy 20%: Upgrading My Home AI Cluster ~ VoxCPM
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ voxel game
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ voxel Rubik's cube
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ voxels
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ voxels
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
ML Frontier #02: In-Context Reinforcement Learning ~ voyager
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ VQWiki
AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop ~ VRAM
W
Made Visible #1: A Microkernel's Storage, Drawn ~ W25Q32
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Lucy 20%: Upgrading My Home AI Cluster ~ Wan 2.2
Bucket List #1: Things I've Always Wanted to Build
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ Ward Cunningham
Five ML Concepts - #24 ~ warmup
Array Languages #1: X_eTaL, an Array Language You Can Read ~ WASM playground
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ WASM
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ WASM
Neural-Net-RS: An Educational Neural Network Platform ~ WASM
Personal Software #10: A Sudoku That Teaches You the Strategies ~ WASM
Personal Software #11: A Campus for the Public Work ~ WASM
RLM: Recursive Language Models for Massive Context ~ WASM
Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem ~ WASM
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ WASM
Saw #11: Building a Tiny Mixture of Experts Microscope ~ WASM
Saw #12: A Model That Decides, and an Index That Knows ~ WASM
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ WASM
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Small Models (5/6): Max AI Per Watt
rank-wav: Ranking Audio Files by Acoustic Quality ~ WAV files
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ wave tank
midi-cli-rs: Music Generation for AI Coding Agents ~ WAV
AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ web dashboard
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ web demo
music-pipe-rs: Web Demo and Multi-Instrument Arrangements ~ web demo
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ web server
Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24 ~ WebAssembly Forth
Embedded #2: COR24-RS --- Learn Assembly in Your Browser ~ WebAssembly
Neural-Net-RS: An Educational Neural Network Platform ~ WebAssembly
Personal Software #10: A Sudoku That Teaches You the Strategies ~ WebAssembly
RLM: Recursive Language Models for Massive Context ~ WebAssembly
TBT #3: Vector Graphics Games ~ WebAssembly
TBT #4: ToonTalk - Teaching Robots to Program ~ WebAssembly
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ WebAssembly
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ WebAssembly
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs ~ web-sw-cor24-demos
music-pipe-rs: Web Demo and Multi-Instrument Arrangements
Five ML Concepts - #17 ~ weight decay
ML Frontier #01: Neural Collapse ~ weight decay
ML Frontier #05: Grokking --- Delayed Generalization ~ weight decay
Five ML Concepts - #15 ~ weight initialization
Made Visible #3: MLOS, Where Memory Means Something Else ~ weight tiles
How AI Learns Part 3: Weight-Based Learning
Welcome to Software Wrighter Lab
Made Visible #1: A Microkernel's Storage, Drawn ~ wgpu
Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking ~ wgpu
TBT #3: Vector Graphics Games ~ wgpu
Array Languages #17: What Makes a Practical Language, IMHO
Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
Made Visible #3: MLOS, Where Memory Means Something Else
Small Models (6/6): Which Small AI Fits YOUR Laptop?
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ whole-app specialization
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ whole-array parallelism
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra ~ wiki coordination
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ wiki history
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ WikiWikiWeb
Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics ~ wiki
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ wiki
Machine Learning #9: Teaching an Array Language to Say CNN ~ windows
AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ wordcloud
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
Saw #15: agentrail, Correcting the Record ~ workflow tool
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ workflow
Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
TBT #11: APL\360 Revisited ~ workspaces
TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe ~ workspaces
Personal Software #11: A Campus for the Public Work
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Welcome to Software Wrighter Lab
TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW ~ write lock
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
X
Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up ~ x86-64 port
Lucy 20%: Upgrading My Home AI Cluster ~ X99 motherboard
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ X_eTaL Blender
Array Languages #2: X_eTaL-demos, Programs Worth Watching ~ X_eTaL demos
Array Languages #11: Math Equations as X_eTaL Macros ~ X_eTaL equation macro
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ X_eTaL extensions
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ X_eTaL FPGA
Array Languages #6: X_eTaL-games, Rules That Are Arrays ~ X_eTaL games
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New ~ X_eTaL GPU
Array Languages #13: Integrals and Continuous Convolution in X_eTaL ~ X_eTaL integral macro
Array Languages #16: How X_eTaL Evolved, Decision by Decision ~ X_eTaL language design
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ X_eTaL libraries
Array Languages #15: A Parsing Library for X_eTaL Macro Writers ~ X_eTaL macro parsing library
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ X_eTaL macros
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is ~ X_eTaL ML
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo ~ X_eTaL Mojo backend
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702 ~ X_eTaL OpenCL Adreno 702
Array Languages #12: ML Pipelines as X_eTaL Macros ~ X_eTaL pipeline macro
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain ~ X_eTaL to PTX
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks ~ X_eTaL train
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ X_eTaL tuples
Array Languages #14: Types, Lints and Errors in X_eTaL ~ X_eTaL type checking
Array Languages #2: X_eTaL-demos, Programs Worth Watching
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ X_eTaL-demos
Array Languages #4: X_eTaL-extensions, Extending the Machine
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays ~ X_eTaL-extensions
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ X_eTaL-extensions
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
Array Languages #6: X_eTaL-games, Rules That Are Arrays
Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
Array Languages #1: X_eTaL, an Array Language You Can Read ~ X_eTaL
Array Languages #1: X_eTaL, an Array Language You Can Read
Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
Array Languages #11: Math Equations as X_eTaL Macros
Array Languages #12: ML Pipelines as X_eTaL Macros
Array Languages #13: Integrals and Continuous Convolution in X_eTaL
Array Languages #14: Types, Lints and Errors in X_eTaL
Array Languages #15: A Parsing Library for X_eTaL Macro Writers
Array Languages #16: How X_eTaL Evolved, Decision by Decision
Array Languages #17: What Makes a Practical Language, IMHO ~ X_eTaL
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL ~ X_eTaL
Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL ~ X_eTaL
Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ xetal doc
Array Languages #14: Types, Lints and Errors in X_eTaL ~ xetal lint
Saw #14: Guards, Lints, Macros as a Test Bench, and Blender ~ xetal lint
Array Languages #4: X_eTaL-extensions, Extending the Machine ~ xetal-x bridge host
Array Languages #1: X_eTaL, an Array Language You Can Read ~ XeTaL
Rabbit-hole #2: FORTH --- FIND and the Cost of a Name ~ XMX hash
Neural-Net-RS: An Educational Neural Network Platform ~ XOR problem
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ XSkill
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory ~ XSkill
Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images ~ xt fixup
Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language ~ xtlm macro libraries
Personal Software #10: A Sudoku That Teaches You the Strategies ~ X-Wing
Personal Software #10: A Sudoku That Teaches You the Strategies ~ XY-Wing
Y
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ Y combinator
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List ~ YAGNI
Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
JSON et al: A Deep Dive into Data Serialization Formats ~ YAML
Energy-Based Learning: From Hopfield Networks to JEPA ~ Yann LeCun
256 Bytes to 640 Gigabytes: Fifty Years of Memory, in Constant Dollars
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
Bucket List #3: 3D Source Code, Five New Languages, and Visible Compilers ~ Yew
Personal Software #10: A Sudoku That Teaches You the Strategies ~ Yew
Personal Software #11: A Campus for the Public Work ~ Yew
TBT #5: IBM 1130 System Emulator - Experience 1960s Computing ~ Yew
TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History ~ Yew
Cat Finder: Personal Software via Vibe Coding ~ YOLOv8
Array Languages #8: X_eTaL-fpga, Array Programs as Circuits ~ Yosys
Welcome to Software Wrighter Lab ~ YouTube
Z
Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language ~ Z combinator
ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence ~ zero-shot scaling
AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents ~ zero-shot transfer
Machine Learning #9: Teaching an Array Language to Say CNN ~ Zhao 2018

GitHub repositories referenced in posts, sorted alphabetically by URL.

RepositoryBlog Post
https://github.com/XSkill-Agent/XSkill AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
https://github.com/badlogic/pi-mono AI Tools #4: Pi --- The Minimal Agent That Stays Out of the Way
https://github.com/crackanimad0r/MesaOS Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/crackanimad0r/MesaOS Made Visible #2: MesaOS, the Conventional One
https://github.com/hardwarewrighter/X_eTaL-fpga Array Languages #8: X_eTaL-fpga, Array Programs as Circuits
https://github.com/lukehinds/nono AI Tools #5: nono --- Sandboxing Pi Without Breaking the Loop
https://github.com/namgyaaal/avoxelgame Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
https://github.com/smolkaj/eigencube Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
https://github.com/software-wrighter-lab/sw-atlas Saw #12: A Model That Decides, and an Index That Knows
https://github.com/software-wrighter-lab/sw-atlas Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/software-wrighter-lab/sw-campus Personal Software #11: A Campus for the Public Work
https://github.com/softwarewrighter/MesaOS Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/softwarewrighter/MesaOS Made Visible #2: MesaOS, the Conventional One
https://github.com/softwarewrighter/X_eTaL-ML Array Languages #12: ML Pipelines as X_eTaL Macros
https://github.com/softwarewrighter/X_eTaL-ML Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
https://github.com/softwarewrighter/X_eTaL-demos/tree/main/demos/eigencube Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
https://github.com/softwarewrighter/X_eTaL-demos Array Languages #2: X_eTaL-demos, Programs Worth Watching
https://github.com/softwarewrighter/X_eTaL-extensions Array Languages #4: X_eTaL-extensions, Extending the Machine
https://github.com/softwarewrighter/X_eTaL-extensions Array Languages #9: X_eTaL and Blender, Scenes and Animation from Arrays
https://github.com/softwarewrighter/X_eTaL-extensions Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
https://github.com/softwarewrighter/X_eTaL-extensions Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
https://github.com/softwarewrighter/X_eTaL-games Array Languages #6: X_eTaL-games, Rules That Are Arrays
https://github.com/softwarewrighter/X_eTaL-gpu Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
https://github.com/softwarewrighter/X_eTaL-gpu Array Languages #7: X_eTaL-gpu, Array Programs on GPUs Old and New
https://github.com/softwarewrighter/X_eTaL-gpu Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
https://github.com/softwarewrighter/X_eTaL-gpu Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
https://github.com/softwarewrighter/X_eTaL-libraries/tree/main/libs/Equations Array Languages #11: Math Equations as X_eTaL Macros
https://github.com/softwarewrighter/X_eTaL-libraries Array Languages #14: Types, Lints and Errors in X_eTaL
https://github.com/softwarewrighter/X_eTaL-libraries Array Languages #3: X_eTaL-libraries, Extending the Vocabulary and the Language
https://github.com/softwarewrighter/X_eTaL-libraries Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
https://github.com/softwarewrighter/X_eTaL Array Languages #11: Math Equations as X_eTaL Macros
https://github.com/softwarewrighter/X_eTaL Array Languages #13: Integrals and Continuous Convolution in X_eTaL
https://github.com/softwarewrighter/X_eTaL Array Languages #14: Types, Lints and Errors in X_eTaL
https://github.com/softwarewrighter/X_eTaL Array Languages #15: A Parsing Library for X_eTaL Macro Writers
https://github.com/softwarewrighter/X_eTaL Array Languages #16: How X_eTaL Evolved, Decision by Decision
https://github.com/softwarewrighter/X_eTaL Array Languages #17: What Makes a Practical Language, IMHO
https://github.com/softwarewrighter/X_eTaL Array Languages #1: X_eTaL, an Array Language You Can Read
https://github.com/softwarewrighter/X_eTaL Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
https://github.com/softwarewrighter/X_eTaL Saw #14: Guards, Lints, Macros as a Test Bench, and Blender
https://github.com/softwarewrighter/avoxelgame-fork Voxels in an Array Language: A 3D World in Dyalog APL and X_eTaL
https://github.com/softwarewrighter/bdh Small Models (4/6): This AI Has a Visible Brain
https://github.com/softwarewrighter/billion-llm Small Models (5/6): Max AI Per Watt
https://github.com/softwarewrighter/bucketlist Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/softwarewrighter/dytopo-rs DyTopo: Dynamic Topology for Multi-Agent AI
https://github.com/softwarewrighter/efficient-llm Small Models (6/6): Which Small AI Fits YOUR Laptop?
https://github.com/softwarewrighter/eigencube-fork Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
https://github.com/softwarewrighter/engram-poc Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
https://github.com/softwarewrighter/engram-poc Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
https://github.com/softwarewrighter/local-llm-loop AI Tools #6: Evaluating Local Models in a Plan-Execute-Review Loop
https://github.com/softwarewrighter/mHC-poc Deepseek Papers (1/3): mHC - Training Stability at Any Depth
https://github.com/softwarewrighter/many-eyes-learning Many-Eyes Learning: Intrinsic Rewards and Diversity
https://github.com/softwarewrighter/many-eyes-learning Solving Sparse Rewards with Many Eyes
https://github.com/softwarewrighter/midi-cli-rs midi-cli-rs: Extending with Custom Mood Packs
https://github.com/softwarewrighter/midi-cli-rs midi-cli-rs: Music Generation for AI Coding Agents
https://github.com/softwarewrighter/mlplunit Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/softwarewrighter/modular-fork/tree/experimental/rust-demo Array Languages #10: X_eTaL on Metal and CUDA, Through Mojo
https://github.com/softwarewrighter/modular-fork/tree/experimental/rust-demo Rabbit-hole #8: From X_eTaL to the Metal, One Kernel Down Every GPU Toolchain
https://github.com/softwarewrighter/modular-fork/tree/research-qualcomm-adreno-702-gpu/adreno-poc Rabbit-hole #9: X_eTaL and Mojo on a Qualcomm Adreno 702
https://github.com/softwarewrighter/multi-hop-reasoning Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
https://github.com/softwarewrighter/multi-hop-reasoning Multi-Hop Reasoning (2/2): The Distribution Trap
https://github.com/softwarewrighter/music-pipe-rs music-pipe-rs: Unix Pipelines for MIDI Composition
https://github.com/softwarewrighter/music-pipe-rs music-pipe-rs: Web Demo and Multi-Instrument Arrangements
https://github.com/softwarewrighter/pocket-llm Small Models (2/6): AI in Your Pocket
https://github.com/softwarewrighter/rlm-project RLM: Recursive Language Models for Massive Context
https://github.com/softwarewrighter/sleepy-coder Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
https://github.com/softwarewrighter/sleepy-coder Towards Continuous LLM Learning (2): Routing Prevents Forgetting
https://github.com/softwarewrighter/sw-checklist AI Tools #3: sw-checklist --- Reining In AI Coding Agents With a Code-Metrics Ratchet
https://github.com/softwarewrighter/train-trm Small Models (1/6): 976 Parameters Beat Billions
https://github.com/softwarewrighter/vectorcade-games TBT #3: Vector Graphics Games
https://github.com/softwarewrighter/viz-hrm-ft Small Models (3/6): Planner + Doer = Genius
https://github.com/softwarewrighter/wordcloud Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-cli-tools/pjmai-rs Saw #1: pjmai-rs, Rig, and langchain-rust
https://github.com/sw-cli-tools/pjmai-rs Saw #4: All Together Now --- Emacs Meets the Multi-Agent Orchestra
https://github.com/sw-cli-tools/pjmai-rs TBT #6: PJMAI-RS - A Shell That Knows Your Projects
https://github.com/sw-cli-tools/pjmai-rs pjmai-rs: Navigation History and Fuzzy Completion
https://github.com/sw-cli-tools/reg-rs Saw #2: reg-rs, avoid-compaction, and agentrail-rs
https://github.com/sw-cli-tools/reg-rs TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
https://github.com/sw-cli-tools/sw-launcher Personal Software #8: One Ring to Rule Them All --- sw-launcher's Memory Profiles, Heap Budgets, and a Working Scenario A
https://github.com/sw-comp-history/apl-horse-race TBT #1: My First Program Was a Horse Race
https://github.com/sw-comp-history/ibm-1130-rs TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
https://github.com/sw-comp-history/pipelines-rs TBT #2: Pipelines on OS/390
https://github.com/sw-embed/bmp280 Embedded #1: BMP280 Driver --- From Prototype to Patent Proof-of-Concept
https://github.com/sw-embed/cor24-rs Embedded #2: COR24-RS --- Learn Assembly in Your Browser
https://github.com/sw-embed/cor24-rs Rabbit-hole #1: Poor Man's Rust-to-Unsupported-ISA Translator
https://github.com/sw-embed/sw-cor24-apl TBT #11: APL\360 Revisited
https://github.com/sw-embed/sw-cor24-basic TBT #9: UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
https://github.com/sw-embed/sw-cor24-emulator Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-embed/sw-cor24-forth Embedded #3: How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
https://github.com/sw-embed/sw-cor24-forth Rabbit-hole #2: FORTH --- FIND and the Cost of a Name
https://github.com/sw-embed/sw-cor24-forth Rabbit-hole #3: FORTH --- Life After Hashing
https://github.com/sw-embed/sw-cor24-forth Rabbit-hole #4: FORTH --- Dictionary Compaction and Specialized Images
https://github.com/sw-embed/sw-cor24-forth Rabbit-hole #5: FORTH --- Retargetable Codegen and the Forward-Reference Problem
https://github.com/sw-embed/sw-cor24-pascal Dogfooding #1: YAGNI Until You Do --- A Pascal P-Code Bump Allocator Grows a Free List
https://github.com/sw-embed/sw-cor24-plsw Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/sw-embed/sw-tos Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/sw-embed/sw-tos Made Visible #1: A Microkernel's Storage, Drawn
https://github.com/sw-embed/web-sw-cor24-demos Personal Software #9: Vibe-Maintenance --- When AI Agents Don't Just Write Code, They Fix Bugs
https://github.com/sw-embed/web-sw-cor24-plsw TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
https://github.com/sw-embed/web-sw-tos Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/sw-fun/sudoku Personal Software #10: A Sudoku That Teaches You the Strategies
https://github.com/sw-fun/tt-rs TBT #4: ToonTalk - Teaching Robots to Program
https://github.com/sw-game-dev/game-mcp-poc MCP: Teaching Claude to Play (and Trash Talk)
https://github.com/sw-ml-study/Repeated-Sampling Large-Language-Monkeys: Scaling Inference, Not Models
https://github.com/sw-ml-study/cat-finder Cat Finder: Personal Software via Vibe Coding
https://github.com/sw-ml-study/demo-abstract-algebra Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-algorithms Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-category-theory Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-coding-agent AI Tools #7: A Coding Agent Small Enough to Understand
https://github.com/sw-ml-study/demo-combinators Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
https://github.com/sw-ml-study/demo-combinators Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-data-structures Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-decision-model Saw #12: A Model That Decides, and an Index That Knows
https://github.com/sw-ml-study/demo-decision-model Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-ml-study/demo-design-patterns Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-extensions Made Visible #1: A Microkernel's Storage, Drawn
https://github.com/sw-ml-study/demo-extensions Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-file-processing Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-functional-pipelines Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-linear-algebra Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-memory Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-ml-microscope Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-ml-utils Machine Learning #9: Teaching an Array Language to Say CNN
https://github.com/sw-ml-study/demo-ml-utils Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/demo-mlpl-libraries Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/emufpga Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/sw-ml-study/m-poc Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
https://github.com/sw-ml-study/m-poc Made Visible #4: Rosetta M, a Stone with Four Faces
https://github.com/sw-ml-study/m-poc Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-ml-study/moe-microscope Saw #11: Building a Tiny Mixture of Experts Microscope
https://github.com/sw-ml-study/neural-net-rs Neural-Net-RS: An Educational Neural Network Platform
https://github.com/sw-ml-study/reasoning-from-scratch Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-ml-study/sw-mlpl AI Tools #7: A Coding Agent Small Enough to Understand
https://github.com/sw-ml-study/sw-mlpl Array Languages #5: X_eTaL-ML, Where the Machine Learning Is
https://github.com/sw-ml-study/sw-mlpl Machine Learning #9: Teaching an Array Language to Say CNN
https://github.com/sw-ml-study/sw-mlpl Made Visible #1: A Microkernel's Storage, Drawn
https://github.com/sw-ml-study/sw-mlpl Made Visible #4: Rosetta M, a Stone with Four Faces
https://github.com/sw-ml-study/sw-mlpl Rabbit-hole #6: The Sage Bird --- Y Combinators in an Eager Array Language
https://github.com/sw-ml-study/sw-mlpl Saw #10: sw-MLPL General-Purpose Features, Libraries, Extensions, Graphics, and Networking
https://github.com/sw-ml-study/sw-mlpl Saw #11: Building a Tiny Mixture of Experts Microscope
https://github.com/sw-ml-study/sw-mlpl TBT #11: APL\360 Revisited
https://github.com/sw-ml-study/sw-os-ml Bucket List #4: Three Operating Systems and an ML Hardware Emulator
https://github.com/sw-ml-study/sw-os-ml Made Visible #3: MLOS, Where Memory Means Something Else
https://github.com/sw-ml-study/sw-os-ml Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-music-tools/rank-wav-rs rank-wav: Ranking Audio Files by Acoustic Quality
https://github.com/sw-vibe-coding/agentrail-rs AI Tools #2: AgentRail Mid-Saga --- Insert, Reorder, Reopen, Recover
https://github.com/sw-vibe-coding/agentrail-rs Saw #15: agentrail, Correcting the Record
https://github.com/sw-vibe-coding/agentrail-rs Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
https://github.com/sw-vibe-coding/agentrail-rs Saw #5: Sagas, Languages, and Compiler Chains
https://github.com/sw-vibe-coding/all-together-now Saw #6: Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
https://github.com/sw-vibe-coding/rust-to-prolog Saw #7: Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
https://github.com/sw-vibe-coding/sw-apl-workspaces Eigencube: Solving a Rubik's Cube with Linear Algebra, in APLSV and X_eTaL
https://github.com/sw-vibe-coding/sw-apl-workspaces Saw #13: A Second Host in the Cloud, a Word Cloud, and Three Benches to Set Up
https://github.com/sw-vibe-coding/sw-apl Array Languages #1: X_eTaL, an Array Language You Can Read
https://github.com/sw-vibe-coding/sw-apl TBT #11: APL\360 Revisited
https://github.com/sw-vibe-coding/sw-apl TBT #12: The IBM 5100's APLSV --- (B) '75, Birds by Execute, and a Machine That Learns Tic-Tac-Toe
https://github.com/sw-vibe-coding/tuplet Saw #8: Tuplet, Smalltalk-on-BASIC, proto-forth-wasm, sw-MLPL Split, and I2C on COR24
https://github.com/sw-vibe-coding/wiki-rs TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
https://github.com/weagan/Engram Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation

Videos referenced in posts, sorted alphabetically by video title.

VideoBlog Post
90s Pipelines Rust/WASM homage #TBT TBT #2: Pipelines on OS/390
976 parameters is more than billions?! Small Models (1/6): 976 Parameters Beat Billions
AI in Your Pocket Small Models (2/6): AI in Your Pocket
Arcade Wireframes: A Vector Story #TBT TBT #3: Vector Graphics Games
Before PCs: The IBM 1130 Experience #TBT TBT #5: IBM 1130 System Emulator - Experience 1960s Computing
Browser-Based Assembly: COR24 RISC Emulator in Rust Embedded #2: COR24-RS --- Learn Assembly in Your Browser
Can AI Catch a Killer? RLM: Recursive Language Models for Massive Context
Can AI Find a Secret Hidden in War and Peace? RLM: Recursive Language Models for Massive Context
code_report: 1 Problem, 16 Programming Languages Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
code_report: 1 Problem, 5 Programming Languages Rabbit-hole #7: The Phoenix Combinator, and Why X_eTaL Brackets Its Forks
Custom Sandbox Code: RLM and WASM RLM: Recursive Language Models for Massive Context
Deep Networks Fixed by Deepseek mHC Deepseek Papers (1/3): mHC - Training Stability at Any Depth
DeepSeek's Engram Paper Tested on Mac Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
DeepSeek's mHC Fix for Gradient Explosion Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Drop-in Mood Packs: No Code Required midi-cli-rs: Extending with Custom Mood Packs
Engram PoC: Now With CUDA Power Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Find Your Best Sound Fast rank-wav: Ranking Audio Files by Acoustic Quality
Five ML Concepts - #1 Five ML Concepts - #1
Five ML Concepts - #2 Five ML Concepts - #2
Five ML Concepts - #3 Five ML Concepts - #3
Five ML Concepts - #4 Five ML Concepts - #4
Five ML Concepts - #5 Five ML Concepts - #5
Five ML Concepts - #6 Five ML Concepts - #6
Five ML Concepts - #7 Five ML Concepts - #7
Five ML Concepts - #8 Five ML Concepts - #8
Five ML Concepts - #9 Five ML Concepts - #9
Five ML Concepts - #10 Five ML Concepts - #10
Five ML Concepts - #11 Five ML Concepts - #11
Five ML Concepts - #12 Five ML Concepts - #12
Five ML Concepts - #13 Five ML Concepts - #13
Five ML Concepts - #14 Five ML Concepts - #14
Five ML Concepts - #15 Five ML Concepts - #15
Five ML Concepts - #16 Five ML Concepts - #16
Five ML Concepts - #17 Five ML Concepts - #17
Five ML Concepts - #18 Five ML Concepts - #18
Five ML Concepts - #19 Five ML Concepts - #19
Five ML Concepts - #20 Five ML Concepts - #20
Five ML Concepts - #21 Five ML Concepts - #21
Five ML Concepts - #22 Five ML Concepts - #22
Five ML Concepts - #23 Five ML Concepts - #23
Five ML Concepts - #24 Five ML Concepts - #24
Five ML Concepts - #25 Five ML Concepts - #25
Five ML Concepts - #26 Five ML Concepts - #26
Five ML Concepts - #27 Five ML Concepts - #27
Five ML Concepts - #28 Five ML Concepts - #28
Five ML Concepts - #29 Five ML Concepts - #29
Five ML Concepts - 30 Five ML Concepts - #30: The Journey So Far
Given enough eyeballs... Solving Sparse Rewards with Many Eyes
Greek Code, No Lowercase #TBT TBT #1: My First Program Was a Horse Race
Home Lab AI Cluster: Lucy Levels Up Lucy 20%: Upgrading My Home AI Cluster
How AI Reads a Book Too Large for Its Context Window RLM: Recursive Language Models for Massive Context
JSON or Something Better? JSON et al: A Deep Dive into Data Serialization Formats
Learning More About In-Context Learning In-Context Learning Revisited: From Mystery to Engineering
LLM Learns While You Sleep Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
LLM with Training Wheels Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
Local Cat Detection in Rust Cat Finder: Personal Software via Vibe Coding
Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW TBT #10: Mass Compile and PL/EDIT --- 1980s Productivity Tools, Reborn on COR24 PL/SW
Max AI Per Watt Small Models (5/6): Max AI Per Watt
MesaOS memory layout in 3D Made Visible #2: MesaOS, the Conventional One
ML Frontier 1: Neural Collapse ML Frontier #01: Neural Collapse
ML Frontier 2: ICRL (In-Context Reinforcement Learning) ML Frontier #02: In-Context Reinforcement Learning
ML Frontier 3: Structure Beats Scale ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
ML Frontier 4: Is Chain of Thought Real? ML Frontier #04: Is Chain of Thought Real?
ML Frontier 5: Grokking ML Frontier #05: Grokking --- Delayed Generalization
MLOS storage and memory in 3D Made Visible #3: MLOS, Where Memory Means Something Else
More Eyes, Better Learning Many-Eyes Learning: Intrinsic Rewards and Diversity
Music Pipes: Unix Tools for Makers and AI Agents music-pipe-rs: Web Demo and Multi-Instrument Arrangements
Music tool for AI Agents, Built in Rust midi-cli-rs: Music Generation for AI Coding Agents
Planner + Doer = Genius Small Models (3/6): Planner + Doer = Genius
Recursive Language Model implemented, evaluated, explained RLM: Recursive Language Models for Massive Context
reg-rs: Snapshot Regression Testing for CLI Tools TBT #7: reg-rs - Regression Testing from C++ to Java to Rust
Scaling Up Your Vibe Coding TBT #6: PJMAI-RS - A Shell That Knows Your Projects
Sharpen the Saw: Rust AI Tools Saw #1: pjmai-rs, Rig, and langchain-rust
Sharpening 3 Rust Dev Tools Saw #2: reg-rs, avoid-compaction, and agentrail-rs
Sinkhorn on Blackwell (mHC part 2) Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Smarter Agent Communication DyTopo: Dynamic Topology for Multi-Agent AI
SWTOS storage layout in 3D Made Visible #1: A Microkernel's Storage, Drawn
This AI Has a Visible Brain Small Models (4/6): This AI Has a Visible Brain
Trash Talkin' Tic Tac Toe MCP: Teaching Claude to Play (and Trash Talk)
Vibe Coding 90s Classic: ToonTalk/Rust #TBT TBT #4: ToonTalk - Teaching Robots to Program
Watch a Neural Network Learn Neural-Net-RS: An Educational Neural Network Platform
Which Small AI Fits YOUR Laptop? Small Models (6/6): Which Small AI Fits YOUR Laptop?
Why I Let an LLM Compile Native Binaries RLM: Recursive Language Models for Massive Context
Why Your LLM Memory Needs a Gate Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
wiki-rs: Six Wikis, One Engine TBT #8: wiki-rs --- Six Wikis, One Engine, Thirty Years of History
XSkill: A Memory Layer for Multimodal Agents AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents

Research papers referenced in posts, sorted alphabetically by title.

PaperBlog Post
A Baseline for Detecting Misclassified and Out-of-Distribution Examples Five ML Concepts - #12
A Comprehensive Survey of Continual Learning How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
A Faster Algorithm for Reducing the Computational Complexity of Convolutional Neural Networks Machine Learning #9: Teaching an Array Language to Say CNN
A Learning Algorithm for Boltzmann Machines Energy-Based Learning: From Hopfield Networks to JEPA
A Mathematical Framework for Transformer Circuits Five ML Concepts - #29
A Path Towards Autonomous Machine Intelligence Energy-Based Learning: From Hopfield Networks to JEPA
A Survey of Loss Functions for Deep Neural Networks Five ML Concepts - #3
A Survey of Quantization Methods for Efficient Neural Network Inference Five ML Concepts - #9
A survey on Image Data Augmentation for Deep Learning Five ML Concepts - #26
A Survey on Transfer Learning Five ML Concepts - #3
A Tutorial on Energy-Based Learning Energy-Based Learning: From Hopfield Networks to JEPA
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour Five ML Concepts - #24
Adam: A Method for Stochastic Optimization Five ML Concepts - #4
Addressing Cold Start in Recommender Systems Five ML Concepts - #14
An Alternative Trajectory for Generative AI ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
An Alternative Trajectory for Generative AI Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
An Introduction to Variational Autoencoders Five ML Concepts - #26
An overview of gradient descent optimization algorithms Five ML Concepts - #2
Attention Is All You Need Five ML Concepts - #1
Attention Is All You Need Five ML Concepts - #6
Attention Is All You Need Five ML Concepts - #7
Augmenting Self-attention with Persistent Memory Saw #12: A Model That Decides, and an Index That Knows
Auto-Encoding Variational Bayes Five ML Concepts - #20
Auto-Encoding Variational Bayes Five ML Concepts - #5
Batch Normalization: Accelerating Deep Network Training Five ML Concepts - #16
BERT: Pre-training of Deep Bidirectional Transformers Five ML Concepts - #5
BERT: Pre-training of Deep Bidirectional Transformers Five ML Concepts - #6
Between accurate prediction and poor decision making: the AI/ML gap Five ML Concepts - #21
Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data ML Frontier #01: Neural Collapse
Bottom-up Domain-Specific Superintelligence ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Five ML Concepts - #11
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models ML Frontier #04: Is Chain of Thought Real?
Chain-of-Thought Prompting How AI Learns Part 5: Context Engineering & Recursive Reasoning
Concrete Problems in AI Safety Five ML Concepts - #24
Constitutional AI: Harmlessness from AI Feedback Five ML Concepts - #26
Controllable Generation from Pre-trained Language Models Five ML Concepts - #22
Curiosity-driven Exploration by Self-Supervised Prediction Many-Eyes Learning: Intrinsic Rewards and Diversity
Curriculum Learning Five ML Concepts - #19
Cyclical Learning Rates Five ML Concepts - #2
Decision Transformer: Reinforcement Learning via Sequence Modeling ML Frontier #02: In-Context Reinforcement Learning
Decoupled Weight Decay Regularization Five ML Concepts - #17
Deep Double Descent: Where Bigger Models and More Data Can Hurt Five ML Concepts - #25
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model Five ML Concepts - #8
Denoising Diffusion Probabilistic Models Five ML Concepts - #8
Diagnosing Pathological Chain-of-Thought in Reasoning Models ML Frontier #04: Is Chain of Thought Real?
Direct Preference Optimization Five ML Concepts - #2
Direct Preference Optimization How AI Learns Part 1: The Many Meanings of Learning
Direct Preference Optimization How AI Learns Part 3: Weight-Based Learning
Distilling the Knowledge in a Neural Network Five ML Concepts - #10
Distilling the Knowledge in a Neural Network How AI Learns Part 3: Weight-Based Learning
Distribution Shift Five ML Concepts - #18
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning DyTopo: Dynamic Topology for Multi-Agent AI
Editing Factual Knowledge in Language Models How AI Learns Part 4: Memory-Based Learning
Editing Large Language Models: Problems, Methods, and Opportunities Five ML Concepts - #27
Efficient Few-Shot Learning Without Prompts (SetFit) Saw #12: A Model That Decides, and an Index That Knows
Efficient Large-Scale Language Model Training on GPU Clusters Five ML Concepts - #12
Efficient Transformers: A Survey Five ML Concepts - #18
ELLA: Subspace Learning for Lifelong Machine Learning How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
ELLA: Subspace Learning for Lifelong Machine Learning How AI Learns Part 6: Toward Continuous Learning
Emergent Abilities of Large Language Models Five ML Concepts - #23
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Five ML Concepts - #21
Engram: Conditional Memory via Scalable Lookup How AI Learns Part 1: The Many Meanings of Learning
Engram: Conditional Memory via Scalable Lookup How AI Learns Part 4: Memory-Based Learning
Engram: Conditional Memory via Scalable Lookup How AI Learns Part 7: Designing a Continuous Learning Agent
Engram: Conditional Memory via Scalable Lookup Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
Engram: Conditional Memory via Scalable Lookup Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
Experience Replay for Continual Learning Five ML Concepts - #27
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift Five ML Concepts - #15
Fast Inference from Transformers via Speculative Decoding Five ML Concepts - #5
Fast Transformer Decoding Five ML Concepts - #8
FlashAttention: Fast and Memory-Efficient Exact Attention Five ML Concepts - #9
FOREVER: Model-Centric Replay How AI Learns Part 6: Toward Continuous Learning
Generative Adversarial Nets Five ML Concepts - #24
Goodhart's Law and Machine Learning: A Structural Perspective Five ML Concepts - #26
GQA: Training Generalized Multi-Query Transformer Models Five ML Concepts - #7
GraphMERT: Reliable Knowledge Graph Distillation ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Grokking as the Transition from Lazy to Rich Training Dynamics ML Frontier #05: Grokking --- Delayed Generalization
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets Five ML Concepts - #29
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets ML Frontier #05: Grokking --- Delayed Generalization
Hierarchical Reasoning Model Small Models (3/6): Planner + Doer = Genius
ImageNet Classification with Deep Convolutional Neural Networks Five ML Concepts - #10
Improving Interactive In-Context Learning from Natural Language Feedback In-Context Learning Revisited: From Mystery to Engineering
Intriguing properties of neural networks Five ML Concepts - #25
IRPO: Intrinsic Reward Policy Optimization Many-Eyes Learning: Intrinsic Rewards and Diversity
IRPO Solving Sparse Rewards with Many Eyes
Jailbroken: How Does LLM Safety Training Fail? Five ML Concepts - #21
KG-Guided RAG (arXiv) Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
KG-Guided RAG (arXiv) Multi-Hop Reasoning (2/2): The Distribution Trap
Knowledge Graphs are Implicit Reward Models ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
Knowledge Graphs are Implicit Reward Models Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
Language Models are Few-Shot Learners Five ML Concepts - #10
Language Models are Few-Shot Learners Five ML Concepts - #5
Language Models are Few-Shot Learners Five ML Concepts - #6
Language Models are Few-Shot Learners In-Context Learning Revisited: From Mystery to Engineering
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling Large-Language-Monkeys: Scaling Inference, Not Models
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization ML Frontier #04: Is Chain of Thought Real?
Latent Reasoning with Supervised Thinking States ML Frontier #04: Is Chain of Thought Real?
Leakage in Data Mining: Formulation, Detection, and Avoidance Five ML Concepts - #24
Learning to summarize from human feedback Five ML Concepts - #18
Learning Transferable Visual Models (CLIP) Five ML Concepts - #4
Long Short-Term Memory Five ML Concepts - #22
LoRA: Low-Rank Adaptation of Large Language Models Five ML Concepts - #3
LoRA: Low-Rank Adaptation of Large Language Models How AI Learns Part 1: The Many Meanings of Learning
LoRA: Low-Rank Adaptation of Large Language Models How AI Learns Part 3: Weight-Based Learning
LoRA: Low-Rank Adaptation of Large Language Models How AI Learns Part 7: Designing a Continuous Learning Agent
LoRA Small Models (5/6): Max AI Per Watt
Mamba: Linear-Time Sequence Modeling Five ML Concepts - #1
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism Five ML Concepts - #28
mHC: Manifold-Constrained Hyper-Connections Deepseek Papers (1/3): mHC - Training Stability at Any Depth
Mixed Precision Training Five ML Concepts - #8
MobileLLM (ICML 2024) Small Models (2/6): AI in Your Pocket
Neural Collapse Beyond the Unconstrained Features Model ML Frontier #01: Neural Collapse
Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers ML Frontier #01: Neural Collapse
Neural Machine Translation by Jointly Learning to Align and Translate Five ML Concepts - #2
Neural Machine Translation of Rare Words with Subword Units Five ML Concepts - #3
Neural networks and physical systems with emergent collective computational abilities Energy-Based Learning: From Hopfield Networks to JEPA
Neural Turing Machines Five ML Concepts - #27
Omnigrok: Grokking Beyond Algorithmic Data ML Frontier #05: Grokking --- Delayed Generalization
OmniRL: In-Context Reinforcement Learning Across Multiple Tasks ML Frontier #02: In-Context Reinforcement Learning
OmniRL: In-Context Reinforcement Learning Across Multiple Tasks Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory
On Calibration of Modern Neural Networks Five ML Concepts - #13
On Calibration of Modern Neural Networks Five ML Concepts - #16
On Calibration of Modern Neural Networks Five ML Concepts - #25
On Calibration of Modern Neural Networks Saw #12: A Model That Decides, and an Index That Knows
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima Five ML Concepts - #23
On Large-Batch Training for Deep Learning Five ML Concepts - #12
On the Difficulty of Training Recurrent Neural Networks Five ML Concepts - #14
On the Properties of Neural Machine Translation Five ML Concepts - #2
Outcome-Based RL Provably Leads Transformers to Reason ML Frontier #04: Is Chain of Thought Real?
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer Five ML Concepts - #11
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer Five ML Concepts - #27
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer Five ML Concepts - #28
Overcoming catastrophic forgetting in neural networks (EWC) Five ML Concepts - #27
Overcoming Catastrophic Forgetting in Neural Networks Five ML Concepts - #15
Overcoming Catastrophic Forgetting in Neural Networks How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Overcoming Catastrophic Forgetting in Neural Networks How AI Learns Part 6: Toward Continuous Learning
Parameter-Efficient Transfer Learning for NLP How AI Learns Part 3: Weight-Based Learning
Prevalence of Neural Collapse during the terminal phase of deep learning training Five ML Concepts - #29
Progress Measures for Grokking via Mechanistic Interpretability ML Frontier #05: Grokking --- Delayed Generalization
Prompt Injection attack against LLM-integrated Applications Five ML Concepts - #21
Reagent: Reasoning Reward Models for Agents Many-Eyes Learning: Intrinsic Rewards and Diversity
Reagent Solving Sparse Rewards with Many Eyes
REALM: Retrieval-Augmented Language Model Pre-Training How AI Learns Part 4: Memory-Based Learning
Reasoning Models Don't Always Say What They Think ML Frontier #04: Is Chain of Thought Real?
Reasoning Models Struggle to Control their Chains of Thought ML Frontier #04: Is Chain of Thought Real?
Recursive Language Models How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Recursive Language Models How AI Learns Part 5: Context Engineering & Recursive Reasoning
Recursive Language Models How AI Learns Part 7: Designing a Continuous Learning Agent
Recursive Language Models RLM: Recursive Language Models for Massive Context
Reflexion: Language Agents with Verbal Reinforcement Learning ML Frontier #02: In-Context Reinforcement Learning
Relational Inductive Biases, Deep Learning, and Graph Networks Five ML Concepts - #12
Representation Learning: A Review and New Perspectives Five ML Concepts - #25
Rethinking Continual Learning with Progressive Neural Collapse ML Frontier #01: Neural Collapse
Rethinking the Inception Architecture for Computer Vision Five ML Concepts - #17
Rethinking the Inception Architecture for Computer Vision Five ML Concepts - #25
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks Five ML Concepts - #10
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks How AI Learns Part 1: The Many Meanings of Learning
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks How AI Learns Part 4: Memory-Based Learning
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks How AI Learns Part 7: Designing a Continuous Learning Agent
Revisiting Feature Prediction for Learning Visual Representations from Video Energy-Based Learning: From Hopfield Networks to JEPA
RoFormer: Enhanced Transformer with Rotary Position Embedding Five ML Concepts - #6
s1: Simple Test-Time Scaling ML Frontier #04: Is Chain of Thought Real?
Scaling Laws for Neural Language Models Five ML Concepts - #17
Scaling Relationship on Learning Mathematical Reasoning with LLMs Five ML Concepts - #22
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture Energy-Based Learning: From Hopfield Networks to JEPA
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks Saw #12: A Model That Decides, and an Index That Knows
Sequence to Sequence Learning with Neural Networks Five ML Concepts - #10
SGDR: Stochastic Gradient Descent with Warm Restarts Five ML Concepts - #23
Share: Shared LoRA Subspaces for Continual Learning How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
Share: Shared LoRA Subspaces for Continual Learning How AI Learns Part 6: Toward Continuous Learning
Share: Shared LoRA Subspaces for Continual Learning How AI Learns Part 7: Designing a Continuous Learning Agent
Share: Shared LoRA Subspaces for Continual Learning Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
Share: Shared LoRA Subspaces for Continual Learning Towards Continuous LLM Learning (2): Routing Prevents Forgetting
Sharpness-Aware Minimization for Efficiently Improving Generalization Five ML Concepts - #29
Shortcut Learning in Deep Neural Networks Five ML Concepts - #13
Simplifying Transformer Blocks Saw #12: A Model That Decides, and an Index That Knows
Speculative Decoding Paper Small Models (5/6): Max AI Per Watt
Stochastic Gradient Descent as Approximate Bayesian Inference Five ML Concepts - #20
Survey of Hallucination in NLG Five ML Concepts - #1
Test-Time Training for Language Models How AI Learns Part 5: Context Engineering & Recursive Reasoning
The Dragon Hatchling Small Models (4/6): This AI Has a Visible Brain
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Five ML Concepts - #28
The Universal Weight Subspace Hypothesis Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
The Universal Weight Subspace Hypothesis Towards Continuous LLM Learning (2): Routing Prevents Forgetting
The Unreasonable Effectiveness of Data Five ML Concepts - #22
Tiny Recursive Model Small Models (1/6): 976 Parameters Beat Billions
To CoT or not to CoT? CoT Helps Mainly on Math and Symbolic Reasoning ML Frontier #04: Is Chain of Thought Real?
Toolformer: Language Models Can Teach Themselves to Use Tools Five ML Concepts - #23
Towards A Rigorous Science of Interpretable Machine Learning Five ML Concepts - #20
Training Compute-Optimal Large Language Models (Chinchilla) Five ML Concepts - #28
Training Deep Nets with Sublinear Memory Cost Five ML Concepts - #13
Training Language Models to Follow Instructions with Human Feedback How AI Learns Part 3: Weight-Based Learning
Training language models to follow instructions with human feedback Five ML Concepts - #9
Training Large Language Models to Reason in a Continuous Latent Space (COCONUT) ML Frontier #04: Is Chain of Thought Real?
Transformers Learn In-Context by Gradient Descent In-Context Learning Revisited: From Mystery to Engineering
Transformers Learn Temporal Difference Methods for In-Context Reinforcement Learning ML Frontier #02: In-Context Reinforcement Learning
Understanding Deep Learning Requires Rethinking Generalization Five ML Concepts - #16
Understanding the Difficulty of Training Deep Feedforward Neural Networks Five ML Concepts - #15
Understanding the Difficulty of Training Deep Feedforward Neural Networks Neural-Net-RS: An Educational Neural Network Platform
Visualizing the Loss Landscape of Neural Nets Five ML Concepts - #14
Voyager: An Open-Ended Embodied Agent with Large Language Models ML Frontier #02: In-Context Reinforcement Learning
What Can Transformers Learn In-Context? How AI Learns Part 1: The Many Meanings of Learning
What Can Transformers Learn In-Context? How AI Learns Part 5: Context Engineering & Recursive Reasoning
What Explains In-Context Learning in Transformers? In-Context Learning Revisited: From Mystery to Engineering
What Uncertainties Do We Need in Bayesian Deep Learning? Five ML Concepts - #20
Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse ML Frontier #01: Neural Collapse
Word2Vec Five ML Concepts - #1
XSkill: Continual Learning from Experience and Skills in Multimodal Agents AI Tools #1: XSkill --- A Memory Layer for Multimodal Agents
XSkill: Continual Learning from Experience and Skills in Multimodal Agents Saw #3: agentrail-rs --- From Walking Skeleton to Dual Memory