Blog Tags

ab-testing (1) about (1) activation-functions (1) adam-optimizer (1) adapters (1) adversarial-examples (1) agent (1) agentrail (2) agentrail-rs (2) agents (1) ai (1) ai-agents (9) ai-cluster (1) ai-tools (1) alignment (1) all-together-now (2) android (1) apl (2) apple-silicon (3) arc-challenge (1) arcade (1) arch-linux (1) architecture (1) assembler (2) assembly (2) asteroids (1) attention (3) audio (1) autoencoders (1) avoid-compaction (1) axum (1) baby-dragon-hatchling (1) backpropagation (2) basic (2) batch-normalization (1) batch-size (1) battlezone (1) bdh (1) benchmark-leakage (1) benchmarks (1) bert (1) bias-variance (1) blue-green-deployment (1) bmp280 (1) bootstrapping (1) bucket-list (2) c-compiler (2) caching-strategies (1) cag (1) calibration (1) canary-deployment (1) catastrophic-forgetting (3) chain-of-thought (2) checkpointing (1) claude (1) claude-code (4) cli (12) cli-tools (2) cms (1) cnn (1) cold-start (1) compiler (1) compilers (2) compute-optimality (1) computer-vision (1) concept-drift (1) conditional-computation (1) console (1) consolidation (1) constitutional-ai (1) context (1) context-rot (1) context-window (2) continual-learning (4) continuous-learning (4) cor24 (7) correlation-causation (1) cost-quality-tradeoffs (1) covariate-shift (1) creative-coding (1) cross-validation (1) cuda (2) curiosity (1) curriculum-learning (1) curse-of-dimensionality (1) data-augmentation (1) data-drift (1) data-leakage (1) data-scaling (1) decision-transformer (1) deep-learning (1) deepseek (3) deployment (1) developer-tools (5) diffusion (1) distillation (2) distribution-matching (1) distribution-shift (1) domain-specific (1) double-descent (1) dpo (2) dqn (1) drift-detection (1) dropout (1) early-stopping (1) education (3) educational (1) efficient-llm (1) elastic-weight-consolidation (1) elisp (1) ella (1) emacs (2) embedded (5) embedded-hal (1) embedding (1) emergent-behavior (1) emulator (2) emulators (2) encoder-decoder (1) engram (3) ensembling (1) epoch (1) evaluation (1) exploration (2) extensibility (1) failure-analysis (1) few-shot-learning (2) fft (1) fine-tuning (5) five-ml-concepts (30) flash-attention (1) fluidsynth (1) flux (1) forth (1) fpga (2) fuzzing (1) fuzzit (1) game (1) game-dev (1) garageband (1) gemma (1) generalization (1) geometry (1) git (1) goodharts-law (1) gpt (2) gqa (1) gradient-clipping (1) gradient-descent (1) gradient-noise (1) grokking (1) gru (1) hallucination (1) hash-table (1) hierarchical-reasoning (1) home-automation (1) homelab (1) hrm (1) human-in-the-loop (1) i2c (1) ibm (2) ibm-1130 (1) icl (1) icrl (2) in-context-learning (5) inductive-bias (1) inference (1) inference-parallelism (1) integer-basic (1) interpretability (1) interpretable-ai (1) intrinsic-rewards (1) jailbreaks (1) json (1) jsonb (1) jsonl (1) kernel (1) keypunch (1) knowledge-graphs (3) kv-cache (1) label-smoothing (1) langchain (1) language-building (1) languages (1) latency-throughput (1) latent-reasoning (1) latent-space (1) learning (2) learning-rate (2) lisp (1) llama (1) llama-cpp (1) llm (10) local-ai (1) lora (7) loss-function (1) loss-landscapes (1) loss-surface (1) lottery-ticket-hypothesis (1) lstm (1) lucy (1) machine-learning (1) machine-learning-education (1) mainframe (2) mamba (1) manifold-hypothesis (1) maze-solving (1) mcp (1) mechanistic-interpretability (1) memory (4) memory-augmented-networks (1) meta-learning (1) mhc (1) midi (4) minicomputer (1) miscalibration (1) mixed-precision (1) ml-concepts (30) ml-fragility (1) ml-frontier (4) mla (1) mlops (1) mlpl (2) mlx (2) mobilellm (1) mode-collapse (1) model-context-protocol (1) model-editing (1) moe (1) mosh (1) msp430 (1) multi-agent (4) multi-hop-reasoning (2) multimodal (1) multiplexer (1) music (4) mvs (1) neural-collapse (2) neural-networks (1) neurosymbolic (1) no_std (1) object-detection (1) offline-ai (1) onnx (1) ood (1) orchestration (1) os390 (1) overconfidence (1) overfitting (1) p-code-vm (1) paperbanana (1) parameter-routing (1) pascal (2) perceptron (1) perplexity (1) personal-software (7) phi-2 (1) pipelines (1) pjmai (3) planning (2) plsw (2) plugins (1) positional-encoding (1) pre-training (1) precision-recall (1) prediction (1) preference-learning (1) pressure-sensor (1) pretraining (2) printer (1) privacy (1) project-management (2) prolog (1) prompt-injection (1) prompting (2) protobuf (1) pty (1) pythia (1) quantization (1) rag (3) raspberry-pi (1) reasoning (1) recursive-language-models (2) recursive-reasoning (1) reg-rs (1) regression-testing (2) regularization (1) reinforcement-learning (4) rejection-sampling (2) replay (1) replay-buffers (1) representation-learning (2) resnets (1) retirement (1) retrieval (1) retro-computing (1) retro-gaming (1) retrocomputing (3) reward-hacking (1) reward-model (1) rig (1) rlhf (2) rlm (2) rnn (1) roc-auc (1) rope (1) routing (1) rsft (2) rtx-3090 (1) rust (30) safety (1) scaling-laws (1) scouts (2) self-attention (1) self-hosting (2) self-training-instability (1) serialization (1) series-milestone (1) sft (1) shadow-deployment (1) share (1) share-algorithm (1) sharpen-the-saw (7) sharpness-aware-minimization (1) shell (2) shortcut-learning (1) signal-processing (1) sleepy-coder (1) smollm (3) snobol4 (1) softmax (1) sparse-activation (1) sparse-activations (1) sparse-rewards (2) speculative-decoding (2) spurious-correlations (1) sqlite (2) stablelm (1) star-trek (1) steerability (1) superposition (1) svd (1) svg (1) system-reliability (1) tbt (5) teletype (1) temperature (1) tempest (1) testing (1) text-to-image (1) text-to-video (1) threaded-code (1) throwback-thursday (4) tiny-recursive-model (1) tinyllama (1) tmux (1) tokenization (1) toml (1) tool-use (3) tools (1) toontalk (1) topology (1) train-val-test (1) transfer-learning (1) transformer (1) transformers (6) translation (1) trm (1) trs-80 (1) uncertainty-estimation (1) univac-1108 (1) universal-approximation (1) unix-pipes (2) vae (1) vector-database (1) vector-graphics (1) vendoring (1) vibe-coding (17) visual-programming (1) vlm (1) voice-cloning (1) voxcpm (1) wan (1) warmup (1) wasm (8) wav (1) web-demo (1) webassembly (1) weight-decay (1) weight-initialization (1) wiki (1) workflow (1) xskill (1) yaml (1) yew (3) yolo (1)

---

ab-testing

• Five ML Concepts - #16

about

• Welcome to Software Wrighter Lab

activation-functions

• Five ML Concepts - #4

adam-optimizer

• Five ML Concepts - #4

adapters

• How AI Learns Part 6: Toward Continuous Learning

adversarial-examples

• Five ML Concepts - #25

agent

• How AI Learns Part 7: Designing a Continuous Learning Agent

agentrail

• Saw (5/?): Sagas, Languages, and Compiler Chains
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory

agentrail-rs

• Bucket List (2/?): A Landing Page for Software Tools
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs

agents

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents

ai

• Bucket List (1/?): Things I've Always Wanted to Build

ai-agents

• ML Frontier #04: Is Chain of Thought Real?
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• ML Frontier #02: In-Context Reinforcement Learning
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs
• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents
• Welcome to Software Wrighter Lab

ai-cluster

• Lucy 20%: Upgrading My Home AI Cluster

ai-tools

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents

alignment

• How AI Learns Part 3: Weight-Based Learning

all-together-now

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

android

• Small Models (2/6): AI in Your Pocket

apl

• Saw (5/?): Sagas, Languages, and Compiler Chains
• TBT (1/?): My First Program Was a Horse Race

apple-silicon

• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
• Deepseek Papers (1/3): mHC - Training Stability at Any Depth

arc-challenge

• Small Models (3/6): Planner + Doer = Genius

arcade

• TBT (3/?): Vector Graphics Games

arch-linux

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL

architecture

• How AI Learns Part 7: Designing a Continuous Learning Agent

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

assembly

• COR24-RS: Learn Assembly in Your Browser
• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

asteroids

• TBT (3/?): Vector Graphics Games

attention

• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
• Five ML Concepts - #2

audio

• rank-wav: Ranking Audio Files by Acoustic Quality

autoencoders

• Five ML Concepts - #19

avoid-compaction

• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs

axum

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History

baby-dragon-hatchling

• Small Models (4/6): This AI Has a Visible Brain

backpropagation

• Neural-Net-RS: An Educational Neural Network Platform
• Five ML Concepts - #1

basic

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
• Saw (5/?): Sagas, Languages, and Compiler Chains

batch-normalization

• Five ML Concepts - #16

batch-size

• Five ML Concepts - #12

battlezone

• TBT (3/?): Vector Graphics Games

bdh

• Small Models (4/6): This AI Has a Visible Brain

benchmark-leakage

• Five ML Concepts - #17

benchmarks

• Small Models (6/6): Which Small AI Fits YOUR Laptop?

bert

• Five ML Concepts - #6

bias-variance

• Five ML Concepts - #8

blue-green-deployment

• Five ML Concepts - #24

bmp280

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

bootstrapping

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum

bucket-list

• Bucket List (2/?): A Landing Page for Software Tools
• Bucket List (1/?): Things I've Always Wanted to Build

c-compiler

• Saw (5/?): Sagas, Languages, and Compiler Chains
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory

caching-strategies

• Five ML Concepts - #26

cag

• How AI Learns Part 4: Memory-Based Learning

calibration

• Five ML Concepts - #13

canary-deployment

• Five ML Concepts - #23

catastrophic-forgetting

• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
• Five ML Concepts - #15
• Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails

chain-of-thought

• ML Frontier #04: Is Chain of Thought Real?
• Five ML Concepts - #11

checkpointing

• Five ML Concepts - #13

claude

• MCP: Teaching Claude to Play (and Trash Talk)

claude-code

• midi-cli-rs: Music Generation for AI Coding Agents
• Neural-Net-RS: An Educational Neural Network Platform
• Cat Finder: Personal Software via Vibe Coding
• TBT (3/?): Vector Graphics Games

cli

• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs
• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• pjmai-rs: Navigation History and Fuzzy Completion
• rank-wav: Ranking Audio Files by Acoustic Quality
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects
• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents

cli-tools

• Neural-Net-RS: An Educational Neural Network Platform
• Cat Finder: Personal Software via Vibe Coding

cms

• TBT (2/?): Pipelines on OS/390

cnn

• Five ML Concepts - #10

cold-start

• Five ML Concepts - #14

compiler

• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

compilers

• Bucket List (2/?): A Landing Page for Software Tools
• Bucket List (1/?): Things I've Always Wanted to Build

compute-optimality

• Five ML Concepts - #28

computer-vision

• Cat Finder: Personal Software via Vibe Coding

concept-drift

• Five ML Concepts - #17

conditional-computation

• Five ML Concepts - #28

console

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

consolidation

• How AI Learns Part 6: Toward Continuous Learning

constitutional-ai

• Five ML Concepts - #26

context

• How AI Learns Part 5: Context Engineering & Recursive Reasoning

context-rot

• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot

context-window

• RLM: Recursive Language Models for Massive Context
• Five ML Concepts - #7

continual-learning

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents
• Five ML Concepts - #27
• Towards Continuous LLM Learning (2): Routing Prevents Forgetting
• Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails

continuous-learning

• How AI Learns Part 7: Designing a Continuous Learning Agent
• How AI Learns Part 6: Toward Continuous Learning
• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
• How AI Learns Part 1: The Many Meanings of Learning

cor24

• 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 (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (5/?): Sagas, Languages, and Compiler Chains
• Bucket List (2/?): A Landing Page for Software Tools
• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

correlation-causation

• Five ML Concepts - #19

cost-quality-tradeoffs

• Five ML Concepts - #18

covariate-shift

• Five ML Concepts - #19

creative-coding

• Bucket List (1/?): Things I've Always Wanted to Build

cross-validation

• Five ML Concepts - #7

cuda

• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
• Deepseek Papers (1/3): mHC - Training Stability at Any Depth

curiosity

• Many-Eyes Learning: Intrinsic Rewards and Diversity

curriculum-learning

• Five ML Concepts - #19

curse-of-dimensionality

• Five ML Concepts - #15

data-augmentation

• Five ML Concepts - #26

data-drift

• Five ML Concepts - #17

data-leakage

• Five ML Concepts - #24

data-scaling

• Five ML Concepts - #22

decision-transformer

• ML Frontier #02: In-Context Reinforcement Learning

deep-learning

• ML Frontier #01: Neural Collapse

deepseek

• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
• Deepseek Papers (1/3): mHC - Training Stability at Any Depth

deployment

• How AI Learns Part 7: Designing a Continuous Learning Agent

developer-tools

• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs
• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• pjmai-rs: Navigation History and Fuzzy Completion
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects

diffusion

• Five ML Concepts - #8

distillation

• How AI Learns Part 3: Weight-Based Learning
• Five ML Concepts - #10

distribution-matching

• Multi-Hop Reasoning (2/2): The Distribution Trap

distribution-shift

• Five ML Concepts - #11

domain-specific

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence

double-descent

• Five ML Concepts - #25

dpo

• How AI Learns Part 3: Weight-Based Learning
• Five ML Concepts - #2

dqn

• Solving Sparse Rewards with Many Eyes

drift-detection

• Five ML Concepts - #15

dropout

• Five ML Concepts - #9

early-stopping

• Five ML Concepts - #13

education

• COR24-RS: Learn Assembly in Your Browser
• TBT (4/?): ToonTalk - Teaching Robots to Program
• Neural-Net-RS: An Educational Neural Network Platform

educational

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

efficient-llm

• Small Models (6/6): Which Small AI Fits YOUR Laptop?

elastic-weight-consolidation

• Five ML Concepts - #27

elisp

• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra

ella

• How AI Learns Part 6: Toward Continuous Learning

emacs

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra

embedded

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
• COR24-RS: Learn Assembly in Your Browser
• Bucket List (1/?): Things I've Always Wanted to Build
• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept
• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

embedded-hal

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

embedding

• Five ML Concepts - #1

emergent-behavior

• Five ML Concepts - #23

emulator

• COR24-RS: Learn Assembly in Your Browser
• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

emulators

• Bucket List (2/?): A Landing Page for Software Tools
• Bucket List (1/?): Things I've Always Wanted to Build

encoder-decoder

• Five ML Concepts - #10

engram

• How AI Learns Part 4: Memory-Based Learning
• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers

ensembling

• Five ML Concepts - #18

epoch

• Five ML Concepts - #18

evaluation

• How AI Learns Part 7: Designing a Continuous Learning Agent

exploration

• Many-Eyes Learning: Intrinsic Rewards and Diversity
• Solving Sparse Rewards with Many Eyes

extensibility

• midi-cli-rs: Extending with Custom Mood Packs

failure-analysis

• Five ML Concepts - #19

few-shot-learning

• In-Context Learning Revisited: From Mystery to Engineering
• Five ML Concepts - #10

fft

• rank-wav: Ranking Audio Files by Acoustic Quality

fine-tuning

• How AI Learns Part 3: Weight-Based Learning
• How AI Learns Part 1: The Many Meanings of Learning
• Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
• Five ML Concepts - #3
• Small Models (5/6): Max AI Per Watt

five-ml-concepts

• Five ML Concepts - #30: The Journey So Far
• Five ML Concepts - #29
• Five ML Concepts - #28
• Five ML Concepts - #27
• Five ML Concepts - #26
• Five ML Concepts - #25
• Five ML Concepts - #24
• Five ML Concepts - #23
• Five ML Concepts - #22
• Five ML Concepts - #21
• Five ML Concepts - #20
• Five ML Concepts - #19
• Five ML Concepts - #18
• Five ML Concepts - #17
• Five ML Concepts - #16
• Five ML Concepts - #15
• Five ML Concepts - #14
• Five ML Concepts - #13
• Five ML Concepts - #12
• Five ML Concepts - #11
• Five ML Concepts - #10
• Five ML Concepts - #9
• Five ML Concepts - #8
• Five ML Concepts - #7
• Five ML Concepts - #6
• Five ML Concepts - #5
• Five ML Concepts - #4
• Five ML Concepts - #3
• Five ML Concepts - #2
• Five ML Concepts - #1

flash-attention

• Five ML Concepts - #9

fluidsynth

• midi-cli-rs: Music Generation for AI Coding Agents

flux

• Lucy 20%: Upgrading My Home AI Cluster

forth

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum

fpga

• Saw (5/?): Sagas, Languages, and Compiler Chains
• COR24-RS: Learn Assembly in Your Browser

fuzzing

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

fuzzit

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

game

• TBT (1/?): My First Program Was a Horse Race

game-dev

• MCP: Teaching Claude to Play (and Trash Talk)

garageband

• music-pipe-rs: Web Demo and Multi-Instrument Arrangements

gemma

• Small Models (6/6): Which Small AI Fits YOUR Laptop?

generalization

• Five ML Concepts - #16

geometry

• ML Frontier #01: Neural Collapse

git

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History

goodharts-law

• Five ML Concepts - #26

gpt

• In-Context Learning Revisited: From Mystery to Engineering
• Five ML Concepts - #7

gqa

• Five ML Concepts - #7

gradient-clipping

• Five ML Concepts - #14

gradient-descent

• Five ML Concepts - #2

gradient-noise

• Five ML Concepts - #20

grokking

• Five ML Concepts - #29

gru

• Five ML Concepts - #21

hallucination

• Five ML Concepts - #1

hash-table

• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation

hierarchical-reasoning

• Small Models (3/6): Planner + Doer = Genius

home-automation

• Bucket List (1/?): Things I've Always Wanted to Build

homelab

• Lucy 20%: Upgrading My Home AI Cluster

hrm

• Small Models (3/6): Planner + Doer = Genius

human-in-the-loop

• Five ML Concepts - #20

i2c

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

ibm

• TBT (2/?): Pipelines on OS/390
• TBT (1/?): My First Program Was a Horse Race

ibm-1130

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

icl

• In-Context Learning Revisited: From Mystery to Engineering

icrl

• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• ML Frontier #02: In-Context Reinforcement Learning

in-context-learning

• ML Frontier #02: In-Context Reinforcement Learning
• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• How AI Learns Part 1: The Many Meanings of Learning
• In-Context Learning Revisited: From Mystery to Engineering
• Five ML Concepts - #5

inductive-bias

• Five ML Concepts - #12

inference

• Five ML Concepts - #9

inference-parallelism

• Five ML Concepts - #28

integer-basic

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

interpretability

• Five ML Concepts - #20

interpretable-ai

• Small Models (4/6): This AI Has a Visible Brain

intrinsic-rewards

• Many-Eyes Learning: Intrinsic Rewards and Diversity

jailbreaks

• Five ML Concepts - #21

json

• JSON et al: A Deep Dive into Data Serialization Formats

jsonb

• JSON et al: A Deep Dive into Data Serialization Formats

jsonl

• JSON et al: A Deep Dive into Data Serialization Formats

kernel

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum

keypunch

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

knowledge-graphs

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
• Multi-Hop Reasoning (2/2): The Distribution Trap
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

kv-cache

• Five ML Concepts - #8

label-smoothing

• Five ML Concepts - #25

langchain

• Saw (1/?): pjmai-rs, Rig, and langchain-rust

language-building

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum

languages

• Bucket List (2/?): A Landing Page for Software Tools

latency-throughput

• Five ML Concepts - #12

latent-reasoning

• ML Frontier #04: Is Chain of Thought Real?

latent-space

• Five ML Concepts - #5

learning

• Bucket List (1/?): Things I've Always Wanted to Build
• How AI Learns Part 1: The Many Meanings of Learning

learning-rate

• Five ML Concepts - #23
• Five ML Concepts - #2

lisp

• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory

llama

• Small Models (5/6): Max AI Per Watt

llama-cpp

• Small Models (2/6): AI in Your Pocket

llm

• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• How AI Learns Part 7: Designing a Continuous Learning Agent
• How AI Learns Part 6: Toward Continuous Learning
• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• How AI Learns Part 4: Memory-Based Learning
• How AI Learns Part 3: Weight-Based Learning
• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
• How AI Learns Part 1: The Many Meanings of Learning
• RLM: Recursive Language Models for Massive Context
• DyTopo: Dynamic Topology for Multi-Agent AI

local-ai

• Lucy 20%: Upgrading My Home AI Cluster

lora

• How AI Learns Part 3: Weight-Based Learning
• Towards Continuous LLM Learning (2): Routing Prevents Forgetting
• Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
• Five ML Concepts - #3
• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

loss-function

• Five ML Concepts - #3

loss-landscapes

• Five ML Concepts - #14

loss-surface

• Five ML Concepts - #23

lottery-ticket-hypothesis

• Five ML Concepts - #28

lstm

• Five ML Concepts - #22

lucy

• Lucy 20%: Upgrading My Home AI Cluster

machine-learning

• Welcome to Software Wrighter Lab

machine-learning-education

• Five ML Concepts - #30: The Journey So Far

mainframe

• TBT (2/?): Pipelines on OS/390
• TBT (1/?): My First Program Was a Horse Race

mamba

• Five ML Concepts - #1

manifold-hypothesis

• Five ML Concepts - #26

maze-solving

• Small Models (1/6): 976 Parameters Beat Billions

mcp

• MCP: Teaching Claude to Play (and Trash Talk)

mechanistic-interpretability

• Five ML Concepts - #29

memory

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents
• How AI Learns Part 4: Memory-Based Learning
• How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation

memory-augmented-networks

• Five ML Concepts - #27

meta-learning

• In-Context Learning Revisited: From Mystery to Engineering

mhc

• Deepseek Papers (1/3): mHC - Training Stability at Any Depth

midi

• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents

minicomputer

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

miscalibration

• Five ML Concepts - #25

mixed-precision

• Five ML Concepts - #8

ml-concepts

• Five ML Concepts - #30: The Journey So Far
• Five ML Concepts - #29
• Five ML Concepts - #28
• Five ML Concepts - #27
• Five ML Concepts - #26
• Five ML Concepts - #25
• Five ML Concepts - #24
• Five ML Concepts - #23
• Five ML Concepts - #22
• Five ML Concepts - #21
• Five ML Concepts - #20
• Five ML Concepts - #19
• Five ML Concepts - #18
• Five ML Concepts - #17
• Five ML Concepts - #16
• Five ML Concepts - #15
• Five ML Concepts - #14
• Five ML Concepts - #13
• Five ML Concepts - #12
• Five ML Concepts - #11
• Five ML Concepts - #10
• Five ML Concepts - #9
• Five ML Concepts - #8
• Five ML Concepts - #7
• Five ML Concepts - #6
• Five ML Concepts - #5
• Five ML Concepts - #4
• Five ML Concepts - #3
• Five ML Concepts - #2
• Five ML Concepts - #1

ml-fragility

• Five ML Concepts - #18

ml-frontier

• ML Frontier #04: Is Chain of Thought Real?
• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
• ML Frontier #02: In-Context Reinforcement Learning
• ML Frontier #01: Neural Collapse

mla

• Five ML Concepts - #8

mlops

• Five ML Concepts - #21

mlpl

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
• Saw (5/?): Sagas, Languages, and Compiler Chains

mlx

• Multi-Hop Reasoning (2/2): The Distribution Trap
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

mobilellm

• Small Models (2/6): AI in Your Pocket

mode-collapse

• Five ML Concepts - #24

model-context-protocol

• MCP: Teaching Claude to Play (and Trash Talk)

model-editing

• Five ML Concepts - #27

moe

• Five ML Concepts - #11

mosh

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL

msp430

• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

multi-agent

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra
• DyTopo: Dynamic Topology for Multi-Agent AI

multi-hop-reasoning

• Multi-Hop Reasoning (2/2): The Distribution Trap
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

multimodal

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents

multiplexer

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

music

• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents

mvs

• TBT (2/?): Pipelines on OS/390

neural-collapse

• ML Frontier #01: Neural Collapse
• Five ML Concepts - #29

neural-networks

• Neural-Net-RS: An Educational Neural Network Platform

neurosymbolic

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence

no_std

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

object-detection

• Cat Finder: Personal Software via Vibe Coding

offline-ai

• Small Models (2/6): AI in Your Pocket

onnx

• Cat Finder: Personal Software via Vibe Coding

ood

• Five ML Concepts - #12

orchestration

• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra

os390

• TBT (2/?): Pipelines on OS/390

overconfidence

• Five ML Concepts - #16

overfitting

• Five ML Concepts - #3

p-code-vm

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

paperbanana

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

parameter-routing

• Five ML Concepts - #27

pascal

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
• Saw (5/?): Sagas, Languages, and Compiler Chains

perceptron

• Five ML Concepts - #5

perplexity

• Five ML Concepts - #15

personal-software

• pjmai-rs: Navigation History and Fuzzy Completion
• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents
• Neural-Net-RS: An Educational Neural Network Platform
• Cat Finder: Personal Software via Vibe Coding

phi-2

• Small Models (6/6): Which Small AI Fits YOUR Laptop?

pipelines

• TBT (2/?): Pipelines on OS/390

pjmai

• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• pjmai-rs: Navigation History and Fuzzy Completion
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects

planning

• Five ML Concepts - #21
• Small Models (3/6): Planner + Doer = Genius

plsw

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (5/?): Sagas, Languages, and Compiler Chains

plugins

• midi-cli-rs: Extending with Custom Mood Packs

positional-encoding

• Five ML Concepts - #6

pre-training

• Five ML Concepts - #5

precision-recall

• Five ML Concepts - #12

prediction

• Five ML Concepts - #21

preference-learning

• Five ML Concepts - #18

pressure-sensor

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

pretraining

• How AI Learns Part 3: Weight-Based Learning
• How AI Learns Part 1: The Many Meanings of Learning

printer

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

privacy

• Small Models (2/6): AI in Your Pocket

project-management

• pjmai-rs: Navigation History and Fuzzy Completion
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects

prolog

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL

prompt-injection

• Five ML Concepts - #21

prompting

• ML Frontier #04: Is Chain of Thought Real?
• Five ML Concepts - #6

protobuf

• JSON et al: A Deep Dive into Data Serialization Formats

pty

• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra

pythia

• Small Models (5/6): Max AI Per Watt

quantization

• Five ML Concepts - #9

rag

• How AI Learns Part 4: Memory-Based Learning
• How AI Learns Part 1: The Many Meanings of Learning
• Five ML Concepts - #10

raspberry-pi

• Embedded (1/?): BMP280 Driver --- From Prototype to Patent Proof-of-Concept

reasoning

• ML Frontier #04: Is Chain of Thought Real?

recursive-language-models

• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• RLM: Recursive Language Models for Massive Context

recursive-reasoning

• Small Models (1/6): 976 Parameters Beat Billions

reg-rs

• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs

regression-testing

• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs

regularization

• Five ML Concepts - #6

reinforcement-learning

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence
• ML Frontier #02: In-Context Reinforcement Learning
• Many-Eyes Learning: Intrinsic Rewards and Diversity
• Solving Sparse Rewards with Many Eyes

rejection-sampling

• Five ML Concepts - #22
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

replay

• How AI Learns Part 6: Toward Continuous Learning

replay-buffers

• Five ML Concepts - #27

representation-learning

• ML Frontier #01: Neural Collapse
• Five ML Concepts - #25

resnets

• ML Frontier #01: Neural Collapse

retirement

• Bucket List (1/?): Things I've Always Wanted to Build

retrieval

• How AI Learns Part 4: Memory-Based Learning

retro-computing

• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing

retro-gaming

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

retrocomputing

• TBT (3/?): Vector Graphics Games
• TBT (2/?): Pipelines on OS/390
• TBT (1/?): My First Program Was a Horse Race

reward-hacking

• Five ML Concepts - #24

reward-model

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence

rig

• Saw (1/?): pjmai-rs, Rig, and langchain-rust

rlhf

• How AI Learns Part 3: Weight-Based Learning
• Five ML Concepts - #9

rlm

• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• RLM: Recursive Language Models for Massive Context

rnn

• Five ML Concepts - #11

roc-auc

• Five ML Concepts - #14

rope

• Five ML Concepts - #6

routing

• DyTopo: Dynamic Topology for Multi-Agent AI

rsft

• Five ML Concepts - #22
• Multi-Hop Reasoning (2/2): The Distribution Trap

rtx-3090

• Lucy 20%: Upgrading My Home AI Cluster

rust

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (5/?): Sagas, Languages, and Compiler Chains
• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra
• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• COR24-RS: Learn Assembly in Your Browser
• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs
• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator
• Saw (1/?): pjmai-rs, Rig, and langchain-rust
• pjmai-rs: Navigation History and Fuzzy Completion
• rank-wav: Ranking Audio Files by Acoustic Quality
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects
• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents
• TBT (4/?): ToonTalk - Teaching Robots to Program
• Towards Continuous LLM Learning (2): Routing Prevents Forgetting
• Neural-Net-RS: An Educational Neural Network Platform
• Cat Finder: Personal Software via Vibe Coding
• RLM: Recursive Language Models for Massive Context
• TBT (3/?): Vector Graphics Games
• DyTopo: Dynamic Topology for Multi-Agent AI
• Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
• TBT (2/?): Pipelines on OS/390
• MCP: Teaching Claude to Play (and Trash Talk)
• Welcome to Software Wrighter Lab

safety

• How AI Learns Part 7: Designing a Continuous Learning Agent

scaling-laws

• Five ML Concepts - #17

scouts

• Many-Eyes Learning: Intrinsic Rewards and Diversity
• Solving Sparse Rewards with Many Eyes

self-attention

• Five ML Concepts - #7

self-hosting

• 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

self-training-instability

• Five ML Concepts - #29

serialization

• JSON et al: A Deep Dive into Data Serialization Formats

series-milestone

• Five ML Concepts - #30: The Journey So Far

sft

• ML Frontier #03: Structure Beats Scale --- Knowledge Graphs and Domain-Specific Superintelligence

shadow-deployment

• Five ML Concepts - #17

share

• How AI Learns Part 6: Toward Continuous Learning

share-algorithm

• Towards Continuous LLM Learning (2): Routing Prevents Forgetting

sharpen-the-saw

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL
• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics
• Saw (5/?): Sagas, Languages, and Compiler Chains
• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs
• Saw (1/?): pjmai-rs, Rig, and langchain-rust

sharpness-aware-minimization

• Five ML Concepts - #29

shell

• pjmai-rs: Navigation History and Fuzzy Completion
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects

shortcut-learning

• Five ML Concepts - #13

signal-processing

• rank-wav: Ranking Audio Files by Acoustic Quality

sleepy-coder

• Towards Continuous LLM Learning (2): Routing Prevents Forgetting

smollm

• Multi-Hop Reasoning (2/2): The Distribution Trap
• Small Models (6/6): Which Small AI Fits YOUR Laptop?
• Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs

snobol4

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

softmax

• Five ML Concepts - #11

sparse-activation

• Five ML Concepts - #28

sparse-activations

• Small Models (4/6): This AI Has a Visible Brain

sparse-rewards

• Many-Eyes Learning: Intrinsic Rewards and Diversity
• Solving Sparse Rewards with Many Eyes

speculative-decoding

• Five ML Concepts - #5
• Small Models (5/6): Max AI Per Watt

spurious-correlations

• Five ML Concepts - #14

sqlite

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust

stablelm

• Small Models (5/6): Max AI Per Watt

star-trek

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

steerability

• Five ML Concepts - #22

superposition

• Five ML Concepts - #4

svd

• Towards Continuous LLM Learning (2): Routing Prevents Forgetting

svg

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

system-reliability

• Five ML Concepts - #22

tbt

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust
• TBT (6/?): PJMAI-RS - A Shell That Knows Your Projects
• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
• TBT (4/?): ToonTalk - Teaching Robots to Program

teletype

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

temperature

• Five ML Concepts - #2

tempest

• TBT (3/?): Vector Graphics Games

testing

• TBT (7/?): reg-rs - Regression Testing from C++ to Java to Rust

text-to-image

• Lucy 20%: Upgrading My Home AI Cluster

text-to-video

• Lucy 20%: Upgrading My Home AI Cluster

threaded-code

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum

throwback-thursday

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
• TBT (3/?): Vector Graphics Games
• TBT (2/?): Pipelines on OS/390
• TBT (1/?): My First Program Was a Horse Race

tiny-recursive-model

• Small Models (1/6): 976 Parameters Beat Billions

tinyllama

• Small Models (5/6): Max AI Per Watt

tmux

• Saw (7/?): Prolog, Many-Agent Isolation, Self-Hosting Assembler, and MLPL

tokenization

• Five ML Concepts - #3

toml

• JSON et al: A Deep Dive into Data Serialization Formats

tool-use

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents
• How AI Learns Part 5: Context Engineering & Recursive Reasoning
• Five ML Concepts - #23

tools

• Bucket List (2/?): A Landing Page for Software Tools

toontalk

• TBT (4/?): ToonTalk - Teaching Robots to Program

topology

• DyTopo: Dynamic Topology for Multi-Agent AI

train-val-test

• Five ML Concepts - #16

transfer-learning

• Five ML Concepts - #4

transformer

• Five ML Concepts - #1

transformers

• ML Frontier #02: In-Context Reinforcement Learning
• ML Frontier #01: Neural Collapse
• In-Context Learning Revisited: From Mystery to Engineering
• Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
• Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
• Deepseek Papers (1/3): mHC - Training Stability at Any Depth

translation

• Rabbit-hole (1/?): Poor Man's Rust-to-Unsupported-ISA Translator

trm

• Small Models (1/6): 976 Parameters Beat Billions

trs-80

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

uncertainty-estimation

• Five ML Concepts - #20

univac-1108

• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC

universal-approximation

• Five ML Concepts - #13

unix-pipes

• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition

vae

• Five ML Concepts - #20

vector-database

• How AI Learns Part 4: Memory-Based Learning

vector-graphics

• TBT (3/?): Vector Graphics Games

vendoring

• Saw (6/?): Agent Coordination, Fuzzing Tests, Vendoring, and Emacs Graphics

vibe-coding

• Embedded (3/?): How Much of Forth Can Be Forth? A Kernel Self-Hosting Spectrum
• TBT (9/?): UNIVAC Startrek, TRS-80 Adventures, and COR24 BASIC
• Saw (5/?): Sagas, Languages, and Compiler Chains
• Bucket List (2/?): A Landing Page for Software Tools
• Saw (4/?): All Together Now --- Emacs Meets the Multi-Agent Orchestra
• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• Saw (3/?): agentrail-rs --- From Walking Skeleton to Dual Memory
• COR24-RS: Learn Assembly in Your Browser
• music-pipe-rs: Web Demo and Multi-Instrument Arrangements
• music-pipe-rs: Unix Pipelines for MIDI Composition
• midi-cli-rs: Extending with Custom Mood Packs
• midi-cli-rs: Music Generation for AI Coding Agents
• TBT (4/?): ToonTalk - Teaching Robots to Program
• Neural-Net-RS: An Educational Neural Network Platform
• Cat Finder: Personal Software via Vibe Coding
• TBT (3/?): Vector Graphics Games
• TBT (2/?): Pipelines on OS/390

visual-programming

• TBT (4/?): ToonTalk - Teaching Robots to Program

vlm

• Five ML Concepts - #4

voice-cloning

• Lucy 20%: Upgrading My Home AI Cluster

voxcpm

• Lucy 20%: Upgrading My Home AI Cluster

wan

• Lucy 20%: Upgrading My Home AI Cluster

warmup

• Five ML Concepts - #24

wasm

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• COR24-RS: Learn Assembly in Your Browser
• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
• Neural-Net-RS: An Educational Neural Network Platform
• RLM: Recursive Language Models for Massive Context
• TBT (3/?): Vector Graphics Games
• MCP: Teaching Claude to Play (and Trash Talk)
• Welcome to Software Wrighter Lab

wav

• rank-wav: Ranking Audio Files by Acoustic Quality

web-demo

• music-pipe-rs: Web Demo and Multi-Instrument Arrangements

webassembly

• TBT (4/?): ToonTalk - Teaching Robots to Program

weight-decay

• Five ML Concepts - #17

weight-initialization

• Five ML Concepts - #15

wiki

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History

workflow

• Saw (2/?): reg-rs, avoid-compaction, and agentrail-rs

xskill

• AI Tools (1/?): XSkill --- A Memory Layer for Multimodal Agents

yaml

• JSON et al: A Deep Dive into Data Serialization Formats

yew

• TBT (8/?): wiki-rs --- Six Wikis, One Engine, Thirty Years of History
• TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
• MCP: Teaching Claude to Play (and Trash Talk)

yolo

• Cat Finder: Personal Software via Vibe Coding