Blog Tags
ab-testing (1)
about (1)
activation-functions (1)
adam-optimizer (1)
adapters (1)
adversarial-examples (1)
agent (1)
ai-agents (4)
ai-cluster (1)
alignment (1)
android (1)
apl (1)
apple-silicon (3)
arc-challenge (1)
arcade (1)
architecture (1)
asteroids (1)
attention (3)
autoencoders (1)
baby-dragon-hatchling (1)
backpropagation (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)
caching-strategies (1)
cag (1)
calibration (1)
canary-deployment (1)
catastrophic-forgetting (3)
chain-of-thought (1)
checkpointing (1)
claude (1)
claude-code (4)
cli (4)
cli-tools (2)
cms (1)
cnn (1)
cold-start (1)
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 (3)
continuous-learning (4)
correlation-causation (1)
cost-quality-tradeoffs (1)
covariate-shift (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)
deepseek (3)
deployment (1)
diffusion (1)
distillation (2)
distribution-matching (1)
distribution-shift (1)
double-descent (1)
dpo (2)
dqn (1)
drift-detection (1)
dropout (1)
early-stopping (1)
education (2)
educational (1)
efficient-llm (1)
elastic-weight-consolidation (1)
ella (1)
embedding (1)
emergent-behavior (1)
emulator (1)
encoder-decoder (1)
engram (3)
ensembling (1)
epoch (1)
evaluation (1)
exploration (2)
extensibility (1)
failure-analysis (1)
few-shot-learning (2)
fine-tuning (5)
five-ml-concepts (29)
flash-attention (1)
fluidsynth (1)
flux (1)
game (1)
game-dev (1)
garageband (1)
gemma (1)
generalization (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)
homelab (1)
hrm (1)
human-in-the-loop (1)
ibm (2)
ibm-1130 (1)
icl (1)
in-context-learning (4)
inductive-bias (1)
inference (1)
inference-parallelism (1)
interpretability (1)
interpretable-ai (1)
intrinsic-rewards (1)
jailbreaks (1)
json (1)
jsonb (1)
jsonl (1)
keypunch (1)
knowledge-graphs (2)
kv-cache (1)
label-smoothing (1)
latency-throughput (1)
latent-space (1)
learning (1)
learning-rate (2)
llama (1)
llama-cpp (1)
llm (9)
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)
mainframe (2)
mamba (1)
manifold-hypothesis (1)
maze-solving (1)
mcp (1)
mechanistic-interpretability (1)
memory (3)
memory-augmented-networks (1)
meta-learning (1)
mhc (1)
midi (4)
minicomputer (1)
miscalibration (1)
mixed-precision (1)
ml-concepts (29)
ml-fragility (1)
mla (1)
mlops (1)
mlx (2)
mobilellm (1)
mode-collapse (1)
model-context-protocol (1)
model-editing (1)
moe (1)
multi-agent (1)
multi-hop-reasoning (2)
music (4)
mvs (1)
neural-collapse (1)
neural-networks (1)
object-detection (1)
offline-ai (1)
onnx (1)
ood (1)
os390 (1)
overconfidence (1)
overfitting (1)
parameter-routing (1)
perceptron (1)
perplexity (1)
personal-software (6)
phi-2 (1)
pipelines (1)
planning (2)
plugins (1)
positional-encoding (1)
pre-training (1)
precision-recall (1)
prediction (1)
preference-learning (1)
pretraining (2)
printer (1)
privacy (1)
prompt-injection (1)
prompting (1)
protobuf (1)
pythia (1)
quantization (1)
rag (3)
recursive-language-models (2)
recursive-reasoning (1)
regularization (1)
reinforcement-learning (2)
rejection-sampling (2)
replay (1)
replay-buffers (1)
representation-learning (1)
retrieval (1)
retro-computing (1)
retrocomputing (3)
reward-hacking (1)
rlhf (2)
rlm (2)
rnn (1)
roc-auc (1)
rope (1)
routing (1)
rsft (2)
rtx-3090 (1)
rust (16)
safety (1)
scaling-laws (1)
scouts (2)
self-attention (1)
self-training-instability (1)
serialization (1)
shadow-deployment (1)
share (1)
share-algorithm (1)
sharpness-aware-minimization (1)
shortcut-learning (1)
sleepy-coder (1)
smollm (3)
softmax (1)
sparse-activation (1)
sparse-activations (1)
sparse-rewards (2)
speculative-decoding (2)
spurious-correlations (1)
stablelm (1)
steerability (1)
superposition (1)
svd (1)
system-reliability (1)
tbt (2)
temperature (1)
tempest (1)
text-to-image (1)
text-to-video (1)
throwback-thursday (3)
tiny-recursive-model (1)
tinyllama (1)
tokenization (1)
toml (1)
tool-use (2)
toontalk (1)
topology (1)
train-val-test (1)
transfer-learning (1)
transformer (1)
transformers (4)
trm (1)
uncertainty-estimation (1)
universal-approximation (1)
unix-pipes (2)
vae (1)
vector-database (1)
vector-graphics (1)
vibe-coding (9)
visual-programming (1)
vlm (1)
voice-cloning (1)
voxcpm (1)
wan (1)
warmup (1)
wasm (6)
web-demo (1)
webassembly (1)
weight-decay (1)
weight-initialization (1)
yaml (1)
yew (2)
yolo (1)
ab-testing
- February 19, 2026 Five ML Concepts - #16
about
- January 30, 2026 Welcome to Software Wrighter Lab
activation-functions
- February 7, 2026 Five ML Concepts - #4
adam-optimizer
- February 7, 2026 Five ML Concepts - #4
adapters
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
adversarial-examples
- February 28, 2026 Five ML Concepts - #25
agent
ai-agents
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
- January 30, 2026 Welcome to Software Wrighter Lab
ai-cluster
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
alignment
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
android
- February 1, 2026 Small Models (2/6): AI in Your Pocket
apl
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
apple-silicon
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
- February 1, 2026 Deepseek Papers (1/3): mHC - Training Stability at Any Depth
arc-challenge
- February 2, 2026 Small Models (3/6): Planner + Doer = Genius
arcade
- February 13, 2026 TBT (3/?): Vector Graphics Games
architecture
asteroids
- February 13, 2026 TBT (3/?): Vector Graphics Games
attention
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
- February 5, 2026 Five ML Concepts - #2
autoencoders
- February 22, 2026 Five ML Concepts - #19
baby-dragon-hatchling
- February 3, 2026 Small Models (4/6): This AI Has a Visible Brain
backpropagation
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 4, 2026 Five ML Concepts - #1
batch-normalization
- February 19, 2026 Five ML Concepts - #16
batch-size
- February 15, 2026 Five ML Concepts - #12
battlezone
- February 13, 2026 TBT (3/?): Vector Graphics Games
bdh
- February 3, 2026 Small Models (4/6): This AI Has a Visible Brain
benchmark-leakage
- February 20, 2026 Five ML Concepts - #17
benchmarks
- February 5, 2026 Small Models (6/6): Which Small AI Fits YOUR Laptop?
bert
- February 9, 2026 Five ML Concepts - #6
bias-variance
- February 11, 2026 Five ML Concepts - #8
blue-green-deployment
- February 27, 2026 Five ML Concepts - #24
caching-strategies
- March 1, 2026 Five ML Concepts - #26
cag
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
calibration
- February 16, 2026 Five ML Concepts - #13
canary-deployment
- February 26, 2026 Five ML Concepts - #23
catastrophic-forgetting
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
- February 18, 2026 Five ML Concepts - #15
- February 12, 2026 Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
chain-of-thought
- February 14, 2026 Five ML Concepts - #11
checkpointing
- February 16, 2026 Five ML Concepts - #13
claude
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
claude-code
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
- February 13, 2026 TBT (3/?): Vector Graphics Games
cli
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
cli-tools
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
cms
- February 5, 2026 TBT (2/?): Pipelines on OS/390
cnn
- February 13, 2026 Five ML Concepts - #10
cold-start
- February 17, 2026 Five ML Concepts - #14
compute-optimality
- March 3, 2026 Five ML Concepts - #28
computer-vision
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
concept-drift
- February 20, 2026 Five ML Concepts - #17
conditional-computation
- March 3, 2026 Five ML Concepts - #28
console
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
consolidation
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
constitutional-ai
- March 1, 2026 Five ML Concepts - #26
context
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
context-rot
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
context-window
- February 13, 2026 RLM: Recursive Language Models for Massive Context
- February 10, 2026 Five ML Concepts - #7
continual-learning
- March 2, 2026 Five ML Concepts - #27
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
- February 12, 2026 Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
continuous-learning
- March 2, 2026 How AI Learns Part 7: Designing a Continuous Learning Agent
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
correlation-causation
- February 22, 2026 Five ML Concepts - #19
cost-quality-tradeoffs
- February 21, 2026 Five ML Concepts - #18
covariate-shift
- February 22, 2026 Five ML Concepts - #19
cross-validation
- February 10, 2026 Five ML Concepts - #7
cuda
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
- February 1, 2026 Deepseek Papers (1/3): mHC - Training Stability at Any Depth
curiosity
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
curriculum-learning
- February 22, 2026 Five ML Concepts - #19
curse-of-dimensionality
- February 18, 2026 Five ML Concepts - #15
data-augmentation
- March 1, 2026 Five ML Concepts - #26
data-drift
- February 20, 2026 Five ML Concepts - #17
data-leakage
- February 27, 2026 Five ML Concepts - #24
data-scaling
- February 25, 2026 Five ML Concepts - #22
deepseek
- February 11, 2026 Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
- February 1, 2026 Deepseek Papers (1/3): mHC - Training Stability at Any Depth
deployment
diffusion
- February 11, 2026 Five ML Concepts - #8
distillation
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 13, 2026 Five ML Concepts - #10
distribution-matching
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
distribution-shift
- February 14, 2026 Five ML Concepts - #11
double-descent
- February 28, 2026 Five ML Concepts - #25
dpo
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 5, 2026 Five ML Concepts - #2
dqn
- February 3, 2026 Solving Sparse Rewards with Many Eyes
drift-detection
- February 18, 2026 Five ML Concepts - #15
dropout
- February 12, 2026 Five ML Concepts - #9
early-stopping
- February 16, 2026 Five ML Concepts - #13
education
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
educational
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
efficient-llm
- February 5, 2026 Small Models (6/6): Which Small AI Fits YOUR Laptop?
elastic-weight-consolidation
- March 2, 2026 Five ML Concepts - #27
ella
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
embedding
- February 4, 2026 Five ML Concepts - #1
emergent-behavior
- February 26, 2026 Five ML Concepts - #23
emulator
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
encoder-decoder
- February 13, 2026 Five ML Concepts - #10
engram
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
- February 11, 2026 Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
ensembling
- February 21, 2026 Five ML Concepts - #18
epoch
- February 21, 2026 Five ML Concepts - #18
evaluation
exploration
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
- February 3, 2026 Solving Sparse Rewards with Many Eyes
extensibility
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
failure-analysis
- February 22, 2026 Five ML Concepts - #19
few-shot-learning
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
- February 13, 2026 Five ML Concepts - #10
fine-tuning
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
- February 12, 2026 Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
- February 6, 2026 Five ML Concepts - #3
- February 4, 2026 Small Models (5/6): Max AI Per Watt
five-ml-concepts
- March 4, 2026 Five ML Concepts - #29
- March 3, 2026 Five ML Concepts - #28
- March 2, 2026 Five ML Concepts - #27
- March 1, 2026 Five ML Concepts - #26
- February 28, 2026 Five ML Concepts - #25
- February 27, 2026 Five ML Concepts - #24
- February 26, 2026 Five ML Concepts - #23
- February 25, 2026 Five ML Concepts - #22
- February 24, 2026 Five ML Concepts - #21
- February 23, 2026 Five ML Concepts - #20
- February 22, 2026 Five ML Concepts - #19
- February 21, 2026 Five ML Concepts - #18
- February 20, 2026 Five ML Concepts - #17
- February 19, 2026 Five ML Concepts - #16
- February 18, 2026 Five ML Concepts - #15
- February 17, 2026 Five ML Concepts - #14
- February 16, 2026 Five ML Concepts - #13
- February 15, 2026 Five ML Concepts - #12
- February 14, 2026 Five ML Concepts - #11
- February 13, 2026 Five ML Concepts - #10
- February 12, 2026 Five ML Concepts - #9
- February 11, 2026 Five ML Concepts - #8
- February 10, 2026 Five ML Concepts - #7
- February 9, 2026 Five ML Concepts - #6
- February 8, 2026 Five ML Concepts - #5
- February 7, 2026 Five ML Concepts - #4
- February 6, 2026 Five ML Concepts - #3
- February 5, 2026 Five ML Concepts - #2
- February 4, 2026 Five ML Concepts - #1
flash-attention
- February 12, 2026 Five ML Concepts - #9
fluidsynth
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
flux
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
game
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
game-dev
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
garageband
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
gemma
- February 5, 2026 Small Models (6/6): Which Small AI Fits YOUR Laptop?
generalization
- February 19, 2026 Five ML Concepts - #16
goodharts-law
- March 1, 2026 Five ML Concepts - #26
gpt
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
- February 10, 2026 Five ML Concepts - #7
gqa
- February 10, 2026 Five ML Concepts - #7
gradient-clipping
- February 17, 2026 Five ML Concepts - #14
gradient-descent
- February 5, 2026 Five ML Concepts - #2
gradient-noise
- February 23, 2026 Five ML Concepts - #20
grokking
- March 4, 2026 Five ML Concepts - #29
gru
- February 24, 2026 Five ML Concepts - #21
hallucination
- February 4, 2026 Five ML Concepts - #1
hash-table
hierarchical-reasoning
- February 2, 2026 Small Models (3/6): Planner + Doer = Genius
homelab
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
hrm
- February 2, 2026 Small Models (3/6): Planner + Doer = Genius
human-in-the-loop
- February 23, 2026 Five ML Concepts - #20
ibm
- February 5, 2026 TBT (2/?): Pipelines on OS/390
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
ibm-1130
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
icl
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
in-context-learning
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
- February 8, 2026 Five ML Concepts - #5
inductive-bias
- February 15, 2026 Five ML Concepts - #12
inference
- February 12, 2026 Five ML Concepts - #9
inference-parallelism
- March 3, 2026 Five ML Concepts - #28
interpretability
- February 23, 2026 Five ML Concepts - #20
interpretable-ai
- February 3, 2026 Small Models (4/6): This AI Has a Visible Brain
intrinsic-rewards
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
jailbreaks
- February 24, 2026 Five ML Concepts - #21
json
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
jsonb
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
jsonl
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
keypunch
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
knowledge-graphs
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
kv-cache
- February 11, 2026 Five ML Concepts - #8
label-smoothing
- February 28, 2026 Five ML Concepts - #25
latency-throughput
- February 15, 2026 Five ML Concepts - #12
latent-space
- February 8, 2026 Five ML Concepts - #5
learning
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
learning-rate
- February 26, 2026 Five ML Concepts - #23
- February 5, 2026 Five ML Concepts - #2
llama
- February 4, 2026 Small Models (5/6): Max AI Per Watt
llama-cpp
- February 1, 2026 Small Models (2/6): AI in Your Pocket
llm
- March 2, 2026 How AI Learns Part 7: Designing a Continuous Learning Agent
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
- February 13, 2026 RLM: Recursive Language Models for Massive Context
- February 12, 2026 DyTopo: Dynamic Topology for Multi-Agent AI
local-ai
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
lora
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
- February 12, 2026 Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
- February 11, 2026 Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
- February 6, 2026 Five ML Concepts - #3
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
loss-function
- February 6, 2026 Five ML Concepts - #3
loss-landscapes
- February 17, 2026 Five ML Concepts - #14
loss-surface
- February 26, 2026 Five ML Concepts - #23
lottery-ticket-hypothesis
- March 3, 2026 Five ML Concepts - #28
lstm
- February 25, 2026 Five ML Concepts - #22
lucy
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
machine-learning
- January 30, 2026 Welcome to Software Wrighter Lab
mainframe
- February 5, 2026 TBT (2/?): Pipelines on OS/390
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
mamba
- February 4, 2026 Five ML Concepts - #1
manifold-hypothesis
- March 1, 2026 Five ML Concepts - #26
maze-solving
- January 31, 2026 Small Models (1/6): 976 Parameters Beat Billions
mcp
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
mechanistic-interpretability
- March 4, 2026 Five ML Concepts - #29
memory
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
- February 25, 2026 How AI Learns Part 2: Catastrophic Forgetting vs Context Rot
- February 11, 2026 Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
memory-augmented-networks
- March 2, 2026 Five ML Concepts - #27
meta-learning
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
mhc
- February 1, 2026 Deepseek Papers (1/3): mHC - Training Stability at Any Depth
midi
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
minicomputer
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
miscalibration
- February 28, 2026 Five ML Concepts - #25
mixed-precision
- February 11, 2026 Five ML Concepts - #8
ml-concepts
- March 4, 2026 Five ML Concepts - #29
- March 3, 2026 Five ML Concepts - #28
- March 2, 2026 Five ML Concepts - #27
- March 1, 2026 Five ML Concepts - #26
- February 28, 2026 Five ML Concepts - #25
- February 27, 2026 Five ML Concepts - #24
- February 26, 2026 Five ML Concepts - #23
- February 25, 2026 Five ML Concepts - #22
- February 24, 2026 Five ML Concepts - #21
- February 23, 2026 Five ML Concepts - #20
- February 22, 2026 Five ML Concepts - #19
- February 21, 2026 Five ML Concepts - #18
- February 20, 2026 Five ML Concepts - #17
- February 19, 2026 Five ML Concepts - #16
- February 18, 2026 Five ML Concepts - #15
- February 17, 2026 Five ML Concepts - #14
- February 16, 2026 Five ML Concepts - #13
- February 15, 2026 Five ML Concepts - #12
- February 14, 2026 Five ML Concepts - #11
- February 13, 2026 Five ML Concepts - #10
- February 12, 2026 Five ML Concepts - #9
- February 11, 2026 Five ML Concepts - #8
- February 10, 2026 Five ML Concepts - #7
- February 9, 2026 Five ML Concepts - #6
- February 8, 2026 Five ML Concepts - #5
- February 7, 2026 Five ML Concepts - #4
- February 6, 2026 Five ML Concepts - #3
- February 5, 2026 Five ML Concepts - #2
- February 4, 2026 Five ML Concepts - #1
ml-fragility
- February 21, 2026 Five ML Concepts - #18
mla
- February 11, 2026 Five ML Concepts - #8
mlops
- February 24, 2026 Five ML Concepts - #21
mlx
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
mobilellm
- February 1, 2026 Small Models (2/6): AI in Your Pocket
mode-collapse
- February 27, 2026 Five ML Concepts - #24
model-context-protocol
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
model-editing
- March 2, 2026 Five ML Concepts - #27
moe
- February 14, 2026 Five ML Concepts - #11
multi-agent
- February 12, 2026 DyTopo: Dynamic Topology for Multi-Agent AI
multi-hop-reasoning
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
music
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
mvs
- February 5, 2026 TBT (2/?): Pipelines on OS/390
neural-collapse
- March 4, 2026 Five ML Concepts - #29
neural-networks
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
object-detection
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
offline-ai
- February 1, 2026 Small Models (2/6): AI in Your Pocket
onnx
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
ood
- February 15, 2026 Five ML Concepts - #12
os390
- February 5, 2026 TBT (2/?): Pipelines on OS/390
overconfidence
- February 19, 2026 Five ML Concepts - #16
overfitting
- February 6, 2026 Five ML Concepts - #3
parameter-routing
- March 2, 2026 Five ML Concepts - #27
perceptron
- February 8, 2026 Five ML Concepts - #5
perplexity
- February 18, 2026 Five ML Concepts - #15
personal-software
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
phi-2
- February 5, 2026 Small Models (6/6): Which Small AI Fits YOUR Laptop?
pipelines
- February 5, 2026 TBT (2/?): Pipelines on OS/390
planning
- February 24, 2026 Five ML Concepts - #21
- February 2, 2026 Small Models (3/6): Planner + Doer = Genius
plugins
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
positional-encoding
- February 9, 2026 Five ML Concepts - #6
pre-training
- February 8, 2026 Five ML Concepts - #5
precision-recall
- February 15, 2026 Five ML Concepts - #12
prediction
- February 24, 2026 Five ML Concepts - #21
preference-learning
- February 21, 2026 Five ML Concepts - #18
pretraining
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
printer
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
privacy
- February 1, 2026 Small Models (2/6): AI in Your Pocket
prompt-injection
- February 24, 2026 Five ML Concepts - #21
prompting
- February 9, 2026 Five ML Concepts - #6
protobuf
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
pythia
- February 4, 2026 Small Models (5/6): Max AI Per Watt
quantization
- February 12, 2026 Five ML Concepts - #9
rag
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
- February 24, 2026 How AI Learns Part 1: The Many Meanings of Learning
- February 13, 2026 Five ML Concepts - #10
recursive-language-models
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 13, 2026 RLM: Recursive Language Models for Massive Context
recursive-reasoning
- January 31, 2026 Small Models (1/6): 976 Parameters Beat Billions
regularization
- February 9, 2026 Five ML Concepts - #6
reinforcement-learning
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
- February 3, 2026 Solving Sparse Rewards with Many Eyes
rejection-sampling
- February 25, 2026 Five ML Concepts - #22
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
replay
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
replay-buffers
- March 2, 2026 Five ML Concepts - #27
representation-learning
- February 28, 2026 Five ML Concepts - #25
retrieval
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
retro-computing
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
retrocomputing
- February 13, 2026 TBT (3/?): Vector Graphics Games
- February 5, 2026 TBT (2/?): Pipelines on OS/390
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
reward-hacking
- February 27, 2026 Five ML Concepts - #24
rlhf
- February 26, 2026 How AI Learns Part 3: Weight-Based Learning
- February 12, 2026 Five ML Concepts - #9
rlm
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 13, 2026 RLM: Recursive Language Models for Massive Context
rnn
- February 14, 2026 Five ML Concepts - #11
roc-auc
- February 17, 2026 Five ML Concepts - #14
rope
- February 9, 2026 Five ML Concepts - #6
routing
- February 12, 2026 DyTopo: Dynamic Topology for Multi-Agent AI
rsft
- February 25, 2026 Five ML Concepts - #22
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
rtx-3090
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
rust
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
- February 13, 2026 RLM: Recursive Language Models for Massive Context
- February 13, 2026 TBT (3/?): Vector Graphics Games
- February 12, 2026 DyTopo: Dynamic Topology for Multi-Agent AI
- February 12, 2026 Towards Continuous LLM Learning (1): Sleepy Coder - When Fine-Tuning Fails
- February 5, 2026 TBT (2/?): Pipelines on OS/390
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
- January 30, 2026 Welcome to Software Wrighter Lab
safety
scaling-laws
- February 20, 2026 Five ML Concepts - #17
scouts
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
- February 3, 2026 Solving Sparse Rewards with Many Eyes
self-attention
- February 10, 2026 Five ML Concepts - #7
self-training-instability
- March 4, 2026 Five ML Concepts - #29
serialization
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
shadow-deployment
- February 20, 2026 Five ML Concepts - #17
share
- March 1, 2026 How AI Learns Part 6: Toward Continuous Learning
share-algorithm
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
sharpness-aware-minimization
- March 4, 2026 Five ML Concepts - #29
shortcut-learning
- February 16, 2026 Five ML Concepts - #13
sleepy-coder
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
smollm
- February 18, 2026 Multi-Hop Reasoning (2/2): The Distribution Trap
- February 5, 2026 Small Models (6/6): Which Small AI Fits YOUR Laptop?
- February 1, 2026 Multi-Hop Reasoning (1/2): Training Wheels for Small LLMs
softmax
- February 14, 2026 Five ML Concepts - #11
sparse-activation
- March 3, 2026 Five ML Concepts - #28
sparse-activations
- February 3, 2026 Small Models (4/6): This AI Has a Visible Brain
sparse-rewards
- February 25, 2026 Many-Eyes Learning: Intrinsic Rewards and Diversity
- February 3, 2026 Solving Sparse Rewards with Many Eyes
speculative-decoding
- February 8, 2026 Five ML Concepts - #5
- February 4, 2026 Small Models (5/6): Max AI Per Watt
spurious-correlations
- February 17, 2026 Five ML Concepts - #14
stablelm
- February 4, 2026 Small Models (5/6): Max AI Per Watt
steerability
- February 25, 2026 Five ML Concepts - #22
superposition
- February 7, 2026 Five ML Concepts - #4
svd
- February 18, 2026 Towards Continuous LLM Learning (2): Routing Prevents Forgetting
system-reliability
- February 25, 2026 Five ML Concepts - #22
tbt
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
temperature
- February 5, 2026 Five ML Concepts - #2
tempest
- February 13, 2026 TBT (3/?): Vector Graphics Games
text-to-image
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
text-to-video
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
throwback-thursday
- February 13, 2026 TBT (3/?): Vector Graphics Games
- February 5, 2026 TBT (2/?): Pipelines on OS/390
- January 29, 2026 TBT (1/?): My First Program Was a Horse Race
tiny-recursive-model
- January 31, 2026 Small Models (1/6): 976 Parameters Beat Billions
tinyllama
- February 4, 2026 Small Models (5/6): Max AI Per Watt
tokenization
- February 6, 2026 Five ML Concepts - #3
toml
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
tool-use
- February 28, 2026 How AI Learns Part 5: Context Engineering & Recursive Reasoning
- February 26, 2026 Five ML Concepts - #23
toontalk
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
topology
- February 12, 2026 DyTopo: Dynamic Topology for Multi-Agent AI
train-val-test
- February 19, 2026 Five ML Concepts - #16
transfer-learning
- February 7, 2026 Five ML Concepts - #4
transformer
- February 4, 2026 Five ML Concepts - #1
transformers
- February 22, 2026 In-Context Learning Revisited: From Mystery to Engineering
- February 11, 2026 Deepseek Papers (3/3): Engram Revisited - From Emulation to Implementation
- February 2, 2026 Deepseek Papers (2/3): Engram - Conditional Memory for Transformers
- February 1, 2026 Deepseek Papers (1/3): mHC - Training Stability at Any Depth
trm
- January 31, 2026 Small Models (1/6): 976 Parameters Beat Billions
uncertainty-estimation
- February 23, 2026 Five ML Concepts - #20
universal-approximation
- February 16, 2026 Five ML Concepts - #13
unix-pipes
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
vae
- February 23, 2026 Five ML Concepts - #20
vector-database
- February 27, 2026 How AI Learns Part 4: Memory-Based Learning
vector-graphics
- February 13, 2026 TBT (3/?): Vector Graphics Games
vibe-coding
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
- February 24, 2026 music-pipe-rs: Unix Pipelines for MIDI Composition
- February 23, 2026 midi-cli-rs: Extending with Custom Mood Packs
- February 20, 2026 midi-cli-rs: Music Generation for AI Coding Agents
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding
- February 13, 2026 TBT (3/?): Vector Graphics Games
- February 5, 2026 TBT (2/?): Pipelines on OS/390
visual-programming
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
vlm
- February 7, 2026 Five ML Concepts - #4
voice-cloning
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
voxcpm
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
wan
- February 28, 2026 Lucy 20%: Upgrading My Home AI Cluster
warmup
- February 27, 2026 Five ML Concepts - #24
wasm
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
- February 15, 2026 Neural-Net-RS: An Educational Neural Network Platform
- February 13, 2026 RLM: Recursive Language Models for Massive Context
- February 13, 2026 TBT (3/?): Vector Graphics Games
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
- January 30, 2026 Welcome to Software Wrighter Lab
web-demo
- February 28, 2026 music-pipe-rs: Web Demo and Multi-Instrument Arrangements
webassembly
- February 19, 2026 TBT (4/?): ToonTalk - Teaching Robots to Program
weight-decay
- February 20, 2026 Five ML Concepts - #17
weight-initialization
- February 18, 2026 Five ML Concepts - #15
yaml
- February 21, 2026 JSON et al: A Deep Dive into Data Serialization Formats
yew
- February 26, 2026 TBT (5/?): IBM 1130 System Emulator - Experience 1960s Computing
- February 2, 2026 MCP: Teaching Claude to Play (and Trash Talk)
yolo
- February 14, 2026 Cat Finder: Personal Software via Vibe Coding