Learn

Open this genre →

1. Step 1 What Machine Learning Really Is — Understanding “Learning” Without the Math FREE6 min read
2. Step 2 Loss Functions and Optimization — How a Model Learns From Being Wrong FREE8 min read
3. Step 3 Overfitting and Evaluation Design — Be Suspicious of 99% Accuracy ★ MEMBER8 min read
4. Step 4 Decision Trees and Gradient Boosting — Still the Champion on Tabular Data FREE12 min read
5. Step 5 Unsupervised Learning from Scratch — Clustering and Dimensionality Reduction ★ MEMBER12 min read
6. Step 6 Self-Supervised Learning — The Day Unlabeled Data Became an Asset ★ MEMBER11 min read
7. Step 7 Data Leakage and Experiment Hygiene — When the Score Is Too Good, Suspect It ★ MEMBER10 min read
8. Step 8 Imbalanced Data in Practice — What to Optimize When 99% Is Normal ★ MEMBER10 min read
9. Step 9 ML System Design — The 90% Outside the Model ★ MEMBER8 min read
10. Step 10 What Ratio Should the Validation Split Be — I Swept It, and What Mattered Was the Count, Not the Ratio FREE12 min read

Open this genre →

1. Step 11 Neural Networks from Scratch — From One Neuron to Many Layers FREE7 min read
2. Step 12 Backpropagation from Scratch — It Is All Just the Chain Rule FREE9 min read
3. Step 13 A History of Normalization Layers — From BatchNorm to RMSNorm ★ MEMBER10 min read
4. Step 14 Activation Functions from Scratch — Why Nonlinearity Is Non-Negotiable FREE13 min read
5. Step 15 Weight Initialization and Regularization — What Lets Training Start, and What Keeps It Going ★ MEMBER15 min read
6. Step 16 Hyperparameter Search — Hunches, Grids, and Bayesian Optimization ★ MEMBER12 min read
7. Step 17 Graph Neural Networks from Scratch — Learning from Connections ★ MEMBER12 min read

Open this genre →

1. Step 18 Image Classification from Scratch — The Invention of the Convolution FREE8 min read
2. Step 19 Object Detection from Scratch (from YOLO to DETR) ★ MEMBER9 min read
3. Step 20 The CNN Family Tree — From AlexNet to ResNet and EfficientNet ★ MEMBER8 min read
4. Step 21 The Autonomous Driving Perception Stack from Scratch — What Cameras and LiDAR Each Bring to the Table FREE9 min read
5. Step 22 Anomaly Detection from Scratch — Learning From Normal Alone ★ MEMBER11 min read
6. Step 23 Medical Imaging AI — Validation Design Comes Before the Accuracy Number ★ MEMBER9 min read
7. Step 24 The ImageNet Moment — The Day Deep Learning Won FREE10 min read
8. Step 25 Paper Walkthrough: TurboVLA — Kick the LLM Out of the Loop and Run a Robot Policy at 32 Hz on an RTX 4090 with Under 1 GB of VRAM ★ MEMBER8 min read
9. Step 26 Paper Walkthrough: PhiZero — A World Model That Reasons in a Language of Physics Before It Renders ★ MEMBER10 min read

Open this genre →

1. Step 27 Attention from Scratch — The Heart of the Transformer, Explained Visually FREE8 min read
2. Step 28 Positional Encoding from Scratch — From Absolute Positions to RoPE FREE10 min read
3. Step 29 Tokenizers from Scratch — The Unit an LLM Cuts the World Into FREE10 min read
4. Step 30 A Field Guide to Attention Variants — MQA, GQA, Sliding Windows, Linear Attention FREE9 min read
5. Step 31 The Transformer, End to End — One Token's Journey from Embedding to Output FREE10 min read
6. Step 32 FlashAttention from Scratch — The Paradox of Doing More Math to Go Faster FREE10 min read
7. Step 33 How Long-Context LLMs Work — From RoPE Interpolation to Ring Attention ★ MEMBER11 min read
8. Step 34 Encoder or Decoder — The Fork in the Road Between BERT and GPT ★ MEMBER9 min read
9. Step 35 Build Your Own BPE Tokenizer — Learning Merge Rules, and Getting Punished by Japanese ★ MEMBER11 min read
10. Step 36 Build Your Own Mini GPT — A Language Model in 300 Lines ★ MEMBER12 min read
11. Step 37 Qwen3.8-Next design report explained (arXiv:2608.30320) ★ MEMBER16 min read
12. Step 38 Paper Explained: Why Gated DeltaNet Survives 4-Bit Quantization — NVFP4 W4A4 in a Hybrid 27B ★ MEMBER11 min read
13. Step 39 Paper Walkthrough: Stop Anchoring to Frame One — Scal3R's Multi-Reference Relative Pose Query ★ MEMBER11 min read
14. Step 40 Paper Walkthrough: SAS — Training a Sparse-Attention Block Selector End-to-End With the Language Modeling Loss ★ MEMBER15 min read
15. Step 41 Paper Explained: LimiX-2 — A Tabular Foundation Model That Learns the Whole Table, Not Just the Answer Column ★ MEMBER7 min read
16. Step 42 Paper Deep Dive: Your Transformer Can Hold Two Thoughts at Once — Blend Two Texts and the LLM Still Remembers Both ★ MEMBER9 min read
17. +1 planned

Open this genre →

1. Step 43 Scaling Laws from Scratch — Why Making Models Bigger Makes Them Smarter (and When It Doesn't) FREE9 min read
2. Step 44 The Science of Prompt Engineering — What Is Proven and What Is Folklore FREE7 min read
3. Step 45 Mamba and State Space Models — Handling Sequences Without Attention FREE12 min read
4. Step 46 Building a Pretraining Corpus — From Web Sludge to Textbook Quality FREE10 min read
5. Step 47 LLM Evaluation from Scratch — Reading Benchmarks and the Contamination Problem FREE11 min read
6. Step 48 Why Language Models Hallucinate — The Mechanics and What Actually Helps FREE9 min read
7. Step 49 Test-Time Scaling — How Models Get Better by Thinking Longer FREE13 min read
8. Step 50 Knowledge Distillation from Scratch — Copying a Big Model into a Small One FREE10 min read
9. Step 51 Alignment, Explained — From RLHF to Constitutional AI ★ MEMBER8 min read
10. Step 52 Scaling Skepticism — A Genealogy of the "Just Make It Bigger" Critique ★ MEMBER11 min read
11. Step 53 Paper Walkthrough: Can Anything Catch a Fake Crisis Video? — What RA-Bench Found ★ MEMBER8 min read
12. Step 54 Paper Walkthrough: SA-MRPO — Stop Studying the Subject You've Already Aced ★ MEMBER11 min read
13. Step 55 Paper Explained: Agentic Artifact Creation — Where Generation Ends and Construction Begins ★ MEMBER9 min read
14. Step 56 Paper walkthrough: Puro-2B — pretraining a 2B model from scratch for $6.9K on consumer GPUs ★ MEMBER13 min read
15. Step 57 Paper walkthrough: RealSWE — re-measuring coding agents when the request is just "fix it" ★ MEMBER12 min read
16. Step 58 Paper Explained: FlowBalance — Verifier-Grounded Self-Improvement from a Model's Own Reasoning ★ MEMBER13 min read
17. Step 59 Paper Walkthrough — Feyospace-v1: Seven People, 164k Trajectories, and a Cyber Model ★ MEMBER13 min read
18. Step 60 Paper Explained: OmniEdu — Building an Open Education LLM Around Four Skills: Solve, Place, Diagnose, Guide ★ MEMBER7 min read
19. Step 61 Paper Explained: Beyond Solver Verdicts — When the Solver Says Yes but the Translation Is Wrong ★ MEMBER9 min read
20. Step 62 Paper Explained: Training Object Permanence in World Models — Teaching Video Models That Hidden Things Still Exist ★ MEMBER8 min read
21. Step 63 Paper Explained: Just-in-Time Memory — Curate Agent Memory When You Read It, Not When You Write It ★ MEMBER9 min read
22. Step 64 Paper Explained: Bellman Policy Optimization — Policy Mirror Descent for LLMs, Without a Value Model ★ MEMBER8 min read
23. +14 planned

Open this genre →

1. Step 65 Paper Deep Dive — ViT: Treating an Image Like a Sentence FREE7 min read
2. Step 66 Paper Deep Dive — CLIP: Putting Words and Images on One Map FREE7 min read
3. Step 67 How VLMs Came Together — Wiring a Vision Encoder into an LLM ★ MEMBER8 min read
4. Step 68 BEV Representations From Scratch — Fusing Multiple Cameras Into One Top-Down Map ★ MEMBER8 min read
5. Step 69 Document AI and OCR Today — How an LLM Ends Up Reading Your Invoices ★ MEMBER10 min read
6. Step 70 Video Understanding from Scratch — From a Pile of Frames to a Sense of Time ★ MEMBER8 min read

Open this genre →

1. Step 71 Diffusion Models from the Ground Up — Add Noise, Then Subtract It FREE9 min read
2. Step 72 VAEs from Scratch — Stir Probability into "Compress and Restore" and You Get a Generator FREE10 min read
3. Step 73 The Rise and Fall of GANs — An Invention Trained by Rivalry, and Why Diffusion Won FREE10 min read
4. Step 74 Flow Matching from Scratch — What Came After Diffusion, and Why It Goes Straight ★ MEMBER10 min read
5. Step 75 CFG and Samplers — What the "Strength" Knob in Generative AI Really Does ★ MEMBER8 min read
6. Step 76 The Mathematics of Diffusion — Generation Seen Through Scores and SDEs ★ MEMBER11 min read
7. Step 77 A Practical Map of Image Generation — SD, ControlNet, and Applying LoRA FREE11 min read
8. Step 78 Music and Audio Generation from Scratch — Sound as Tokens ★ MEMBER9 min read
9. Step 79 The State of 3D Generation — From NeRF to Gaussian Splatting ★ MEMBER11 min read
10. Step 80 Build Your Own Diffusion Model — Starting from MNIST ★ MEMBER11 min read

Open this genre →

1. Step 81 Instruction Tuning and RLHF from Scratch — How a Model Learns to Follow Orders FREE9 min read
2. Step 82 Learning Rate Schedules — Why Warmup and Why Cosine FREE10 min read
3. Step 83 Mixed Precision Training — Going Faster in fp16/bf16/fp8 Without Breaking ★ MEMBER10 min read
4. Step 84 LoRA vs. Full Fine-Tuning — What You Give Up, What You Get FREE10 min read
5. Step 85 Building a Dataset in Practice — Collect, Clean, Blend ★ MEMBER11 min read
6. Step 86 DPO and What Came After — The Lineage That Simplified RLHF ★ MEMBER13 min read
7. Step 87 Continual Learning and Catastrophic Forgetting — Why Models Can't Just Keep Learning ★ MEMBER9 min read
8. Step 88 Diagnosing Broken Training — Telling Divergence, NaN, and Plateaus Apart FREE11 min read
9. Step 89 Versioning Data and Models — An Experiment You Cannot Reproduce Never Happened ★ MEMBER11 min read
10. Step 90 Paper Deep-Dive: ABSeeker — Training Long-Horizon Search Agents by Grading Each Step Backward from the Answer ★ MEMBER11 min read
11. Step 91 PAWBench Explained — Can Video Generators Get the Odds Right, Not Just the Physics? ★ MEMBER10 min read
12. Step 92 Paper Walkthrough: PaperGym — Turning One Paper Into a Graded Training Environment for Research Plans ★ MEMBER11 min read
13. Step 93 Paper Walkthrough: StudentSim — Training a Simulator That Is Actually *That* Student ★ MEMBER12 min read
14. Step 94 Paper Walkthrough: It Takes Two to Match — Co-Evolving Both Sides of Retrieval with RL ★ MEMBER13 min read
15. Step 95 Paper Explained: DataFlex-RL — Did 11 RLVR Data Policies Beat Uniform Sampling? Re-measured Over 12 Seeds ★ MEMBER14 min read
16. Step 96 Paper Walkthrough: SpeakerMem-R1 — A Two-Track Memory That Remembers Who Said What, About Whom, and When ★ MEMBER10 min read
17. Step 97 Paper walkthrough: WanPE — turning a video prompt into a director's shooting plan ★ MEMBER8 min read
18. Step 98 Paper Explained: When Wording Changes an AI Reviewer's Score — RobustReview and SciCore ★ MEMBER7 min read
19. Step 99 Paper Deep Dive: Transformers Stop Thinking Too Early — How a One-Layer Rank-8 LoRA Stretches 3-Line Reference Following to 50 ★ MEMBER7 min read
20. Step 100 QLoRA — Fine-Tuning a 65B Model on One GPU FREE19 min read
21. Step 101 LoRA from Scratch — Fine-Tuning a Giant by Training Two Thin Matrices FREE17 min read
22. Step 102 Adam from Scratch — Two Moving Averages and the Correction Nobody Explains FREE18 min read
23. +8 planned

Open this genre →

1. Step 103 The KV Cache from Scratch — The Heart of Fast Inference FREE7 min read
2. Step 104 LLM Quantization from Scratch — Why Losing Precision Doesn't Break It FREE8 min read
3. Step 105 Speculative Decoding from Scratch — How a Tiny Draft Model Speeds Up an LLM Without Changing a Single Output FREE8 min read
4. Step 106 KV Cache Compression — Quantize, Evict, Share Your Way to Cheaper Long-Context Inference FREE9 min read
5. Step 107 LLM Serving from Scratch — vLLM, Continuous Batching, and Not Letting the GPU Idle FREE10 min read
6. Step 108 Structured Output and Constrained Decoding — How to Stop an LLM from Breaking Your JSON FREE11 min read
7. Step 109 Surviving GPU Out-of-Memory — Every Cause, Every Fix FREE11 min read
8. Step 110 Cutting Inference Cost in Practice — What to Do First FREE11 min read
9. Step 111 Prompt Caching and Context Design — One Prefix Rule That Moves Your Bill by an Order of Magnitude FREE10 min read
10. Step 112 Paper Walkthrough: The Personalization Mirage — LLMs Invent a Version of You, and Their Self-Reports Point the Wrong Way FREE9 min read
11. Step 113 Paper Walkthrough: DAPD — Breaking the Teacher's "Cheat-Sheet Illusion" in Distillation with Dual Anchors FREE8 min read
12. Step 114 Paper Walkthrough: CodeNib — A Multi-View Data System That Serves Repository Context to Coding Agents FREE8 min read
13. Step 115 Paper explained: BDH-CQ — an AI that thinks without words. Recurrent memory plus latent reasoning resets ARC's cost frontier FREE8 min read
14. Step 116 Paper Deep-Dive: AgentOPSD — Finding the Turn That Won the Game with Recursive Bayesian Belief Updates FREE9 min read
15. Step 117 Paper Walkthrough: No Gold Answers, No Stronger Teacher — How u-OPSD Distills From Its Own Majority Vote FREE14 min read
16. Step 118 Paper Explained: Agentic ESOpt — Drop Backprop, Jiggle the Weights, and Train Long-Horizon LLM Agents ★ MEMBER15 min read
17. Step 119 Paper Walkthrough — WarpSAC: When RL's Safety Rails Become Handcuffs ★ MEMBER8 min read
18. Step 120 TTPO Explained: Training a Model Mid-Exam, With No Answer Key ★ MEMBER11 min read
19. Step 121 Paper explained: Self-OPD — an image generator that distills itself, with no teacher ★ MEMBER13 min read
20. Step 122 Paper walkthrough: CyberFactory — turning wild CVEs into runnable training problems ★ MEMBER11 min read
21. Step 123 Paper Walkthrough: DART-SD — Training Tool-Calling Agents Without Flattening the Diamond ★ MEMBER12 min read
22. Step 124 SMELT explained (arXiv:2609.01343) — compute-matched looping ★ MEMBER16 min read
23. Step 125 Paper Walkthrough: Normalized Low-Rank Adaptation — Why Normalizing LoRA's Entry Matrix Works ★ MEMBER9 min read
24. Step 126 Paper Walkthrough: From Production Traffic to Post-Training — Folding 200 Internal Apps Into One Self-Hosted LLM ★ MEMBER14 min read
25. Step 127 Paper Explained: Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement ★ MEMBER11 min read
26. Step 128 Paper Explained — LatentPress: Feeding Compressed Context Straight to a Frozen LLM, Neither as Text Nor as Pixels ★ MEMBER12 min read
27. Step 129 Paper Walkthrough: Language Models Can Control Their Own Attention ★ MEMBER9 min read
28. Step 130 Paper Explained: Compile by Training — Turning a Natural-Language Spec into a Function That Runs Locally ★ MEMBER10 min read
29. Step 131 Paper Walkthrough: One Training Example Keeps On-Policy Distillation Improving for Hundreds of Steps ★ MEMBER11 min read
30. Step 132 Paper Walkthrough: Random Attention — Throwing KV Cache Entries Away at Random Works Just as Well ★ MEMBER12 min read
31. Step 133 Paper Walkthrough: On-Policy Reverse Distillation — Borrowing a Weak Teacher's Direction, Not Its Answers ★ MEMBER11 min read
32. Step 134 Paper walkthrough: BeaconKV — evicting KV cache by predicting when a reasoning model will re-read its own plan ★ MEMBER12 min read
33. Step 135 Paper Walkthrough: Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training — training the draft alongside a 122B policy at 256K tokens ★ MEMBER10 min read
34. Step 136 Paper Explained: Steering Geometry — Do LLM Steering Vectors Trace the Map of Human Values? ★ MEMBER7 min read
35. Step 137 Paper Explained: FreeFlow — Optical Flow with a Hierarchical Transformer and No Flow-Specific Parts ★ MEMBER10 min read
36. Step 138 Paper Explained: An Open Recipe for IMO Gold — How Open Models Reached Olympiad Gold with Generate, Verify, Refine ★ MEMBER7 min read
37. Step 139 Paper Explained: When EOS Tokens Disagree — Why On-Policy Distillation Students Forget How to Stop ★ MEMBER7 min read
38. Step 140 Paper Explained: Negative Self-Distillation — Learning to Reason by Steering Away From Your Worst Self ★ MEMBER8 min read
39. Step 141 Paper Explained: IntBMoE — Every Expert Contributes, Yet Each Token Runs Only a Few Blocks ★ MEMBER6 min read
40. Step 142 Paper Explained: DeepSeek-V4.1-Flash — How Far Can KV Cache Compression Go? ★ MEMBER6 min read
41. Step 143 Paper Explained: JEV-as-a-Judge — Accept When Confident, Escalate When Unsure ★ MEMBER6 min read
42. Step 144 Paper Explained: RewardVerse — A Video Reward Model That Writes the Rubric Before It Scores (RGPO) ★ MEMBER8 min read
43. Step 145 Paper Explained: Disaggregated Quantization — Quantize LLM Prefill and Decode Differently ★ MEMBER6 min read
44. Step 146 Paper Explained: Post-Training Leaves Behavioral Shadows on Unrelated Decisions — capability transfer through one unrelated word ★ MEMBER9 min read
45. Step 147 Paper Explained: Beyond Teacher Assignment — Why Choosing the Right Teacher Isn't Enough When You Distill Many Specialists into One Model ★ MEMBER8 min read
46. +23 planned

Open this genre →

1. Step 148 RAG Fundamentals and Design Patterns — Embeddings, Chunking, Reranking, and Evaluation from Scratch FREE8 min read
2. Step 149 RAG vs Fine-Tuning — Which One, and When FREE8 min read
3. Step 150 Embeddings from Scratch — from word2vec Intuition to Contextual Embeddings FREE6 min read
4. Step 151 Recommenders and Embeddings — Same Math as RAG, Different Goal FREE10 min read
5. Step 152 Chunking Strategies — How You Split Decides What You Can Find FREE10 min read
6. Step 153 GraphRAG from Scratch — Where Knowledge Graphs Meet Retrieval ★ MEMBER11 min read
7. Step 154 Evaluating RAG in Practice — Turning “Seems Better” Into a Number ★ MEMBER13 min read
8. Step 155 Build Your Own Vector DB — From Brute Force to HNSW ★ MEMBER13 min read
9. Step 156 Paper Walkthrough: WeMM-Embedding — Putting Text, Images and Video on One Ruler ★ MEMBER13 min read
10. Step 157 Hi-Q explained (arXiv:2608.30468) — multi-hop query refinement ★ MEMBER13 min read
11. Step 158 Paper Explained: Ovis-Embedding — One Ruler for Text, Images, Video, and Audio ★ MEMBER7 min read
12. Step 159 Paper Explained: D-RAC — Normalize Everything to PDF, Read the Pages Once, Then Chunk by ID ★ MEMBER7 min read
13. Step 160 Paper Explained: Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation — Borrow Someone Else's Skill, Rewrite It for Your Own Harness ★ MEMBER8 min read
14. +2 planned

Open this genre →

1. Step 161 LLM Agents from Scratch — Designing the Tool-Use Loop FREE8 min read
2. Step 162 End-to-End Driving from Scratch — Perception to Control in a Single Network FREE9 min read
3. Step 163 MCP and Tool Protocols — The Standard That Connects an Agent's Hands FREE11 min read
4. Step 164 Multi-Agent Design Patterns — Division, Debate, Verification FREE10 min read
5. Step 165 Designing Agent Memory — Short-Term, Long-Term, Episodic FREE11 min read
6. Step 166 Evaluating Agents — How Benchmarks and Harnesses Are Built FREE11 min read
7. Step 167 AlphaGo from Scratch — The Marriage of Search and Learning FREE9 min read
8. Step 168 Build Your Own Agent Loop — The Minimal Shape of Tool Calling FREE8 min read
9. Step 169 Paper Walkthrough: SWE-Bench ProMax — Measuring What Coding Agents Can Really Do with Large-Scale, Multilingual Refactoring FREE7 min read
10. Step 170 Paper Walkthrough: Macaron-V1 — A Frozen Base plus a Mixture of LoRAs, Built to Keep Learning After Launch FREE8 min read
11. Step 171 Paper Walkthrough: EnvACE — Agents That Rehearse the World Instead of Calling It FREE8 min read
12. Step 172 Paper Explained: Video-DeepResearch — Agents That Watch a Video, Then Chase Down Every Lead ★ MEMBER9 min read
13. Step 173 Paper Walkthrough: ToolArtist — Search, Draw, or Redraw? The Image Agent That Decides for Itself ★ MEMBER8 min read
14. Step 174 Paper Deep-Dive: Recursive Synthesis — Extending Verified Tasks Into 40,000 Long-Horizon Terminal Problems ★ MEMBER13 min read
15. Step 175 Paper Walkthrough: Qwen-UI-Agent — How Alibaba Built a GUI Agent That Works on Real Phones and PCs ★ MEMBER10 min read
16. Step 176 Paper Explained: OSReward — Can You Trust the AI That Grades AI? Remeasuring Rewards for Computer-Use Agents FREE10 min read
17. Step 177 Paper Walkthrough: Metis — A 'Memory Foundation Model' That Moves Agent Memory Inside the Model FREE8 min read
18. Step 178 Paper Walkthrough: MerchantBench — Can an LLM Agent Run an Online Store for a Year? Why It Earns Only 27.3% of What Humans Do FREE10 min read
19. Step 179 Paper Walkthrough: Mental World Modeling — A World Model That Advances Minds, Not Just Physics FREE9 min read
20. Step 180 Paper Explained: LongHorizon-Harness — Long-Horizon Agent Tasks Are a State-Management Problem, Not an Execution Problem FREE8 min read
21. Step 181 Paper Deep-Dive: Frontis-MA1 — Training the AI That Builds AI: One Step Toward Recursive Self-Improvement in ML Engineering FREE11 min read
22. Step 182 Paper Walkthrough: ComBodied Agents — Moving an Agent's Target from Software and Matter to the Person FREE11 min read
23. Step 183 Paper Explained: Co-Evolution in Agentic Systems — Three Stages Toward Self-Directed Evolution FREE9 min read
24. Step 184 Paper walkthrough: Zetta ζ — a robot harness that repairs itself mid-execution, with the policy frozen ★ MEMBER13 min read
25. Step 185 Paper Explainer: SemaPLC — The Agent That Isn't Allowed to Say "Done" ★ MEMBER13 min read
26. Step 186 Paper Walkthrough: OmniScientist — An AI Scientist That Actually Looks at the Raw Data ★ MEMBER11 min read
27. Step 187 Paper Walkthrough — FACET: Grounding Instruction, Environment, Solution and Verifier in One Executable State ★ MEMBER12 min read
28. Step 188 Paper Explainer: Why Agent Skills Work — and Where They Break ★ MEMBER9 min read
29. Step 189 Paper Explained: Co-RL — Reasoning Without Labels, Emerging From a Diverse Cohort ★ MEMBER12 min read
30. Step 190 Paper Explained: FreeToken — Treating Your Own PC as a Single Elastic Inference Platform ★ MEMBER13 min read
31. Step 191 Paper Walkthrough: Embodied-Navigator (TAMP-Nav) — Let the VLM Just Point, and Navigation Gets Both Faster and Better ★ MEMBER12 min read
32. Step 192 Paper walkthrough: ASI-Bench — peeling away human guidance to measure what AI can do alone ★ MEMBER10 min read
33. Step 193 Paper Walkthrough: FrontierChallenge — Grading Scientific Work on Whether It Was Actually Delivered ★ MEMBER8 min read
34. Step 194 Paper Explained: JIT-Agent — A Model That Writes the Agent Harness On Demand ★ MEMBER14 min read
35. Step 195 Paper Walkthrough: ZimaBlue — Turning 120,000 Hours of Egocentric Video into Robot Skill ★ MEMBER13 min read
36. Step 196 Paper Explained: What Makes Good Agentic Data? The ACE Lens ★ MEMBER11 min read
37. Step 197 Paper Walkthrough — UrbanGround: Where MLLM Agents Break Down on a Real Street ★ MEMBER10 min read
38. Step 198 Paper Walkthrough: UI-Venus-2 — Taking Screen-Operating Agents From Benchmarks to Real Work ★ MEMBER13 min read
39. Step 199 Paper Walkthrough: Training Agents to Evolve with Their Harness ★ MEMBER15 min read
40. Step 200 Paper Explained: StarHarness — Evolving the Scaffold Instead of the Weights ★ MEMBER13 min read
41. Step 201 Paper Walkthrough: SecOPD — Grading One Token at a Time to Cut Adaptive Prompt Injection by an Order of Magnitude ★ MEMBER11 min read
42. Step 202 Paper Explained: Repo-To-Skill — Distilling GitHub Repositories Into Skills an AI Can Use ★ MEMBER12 min read
43. Step 203 Paper Walkthrough: PILOT in the Loop — Fixing the Run While It Is Still Running ★ MEMBER15 min read
44. Step 204 Paper Walkthrough: LoopArena — Benchmarking the Model That Steers a Coding Agent ★ MEMBER11 min read
45. Step 205 Paper Walkthrough: Code World Model — Putting a Coding Agent in Charge of the World ★ MEMBER14 min read
46. Step 206 Paper Walkthrough: Code as Worlds — An Agent That Writes the World Down as Runnable Code ★ MEMBER13 min read
47. Step 207 Paper Walkthrough: AutoSaddler — Growing a Harness That Doesn't Break, from Agent Failure Logs ★ MEMBER11 min read
48. Step 208 HarnessDev explained (arXiv:2609.01437) — agent harness benchmark ★ MEMBER12 min read
49. Step 209 Paper Walkthrough: EarlyEval — Making Agent Evaluation Cheaper by Stopping Early ★ MEMBER12 min read
50. Step 210 Paper Walkthrough: Aspire — Can Models Self-Evolve from Vague Goals? ★ MEMBER14 min read
51. Step 211 Paper Walkthrough: Terminal-Universe — Turning Agent Logs Back Into Reusable Execution Environments ★ MEMBER13 min read
52. Step 212 CogEvol: What the Reward Cannot Measure, RL Will Quietly Destroy ★ MEMBER9 min read
53. Step 213 Paper walkthrough: Knowing When Not to Reuse — conditional experience transfer in autonomous post-training (BCIT) ★ MEMBER11 min read
54. Step 214 Paper Walkthrough: WHALE — Training the Weights and the Harness in Turns ★ MEMBER12 min read
55. Step 215 Paper Walkthrough: S³Gym — Does Self-Testing and Self-Judging Add Up to Self-Improvement? ★ MEMBER8 min read
56. Step 216 Editable Visual Design, explained — demoting image generation to a sketch and shipping the artifact as HTML ★ MEMBER11 min read
57. Step 217 Paper Deep-Dive: Iris — Reverse-Built Search Tasks and SFT↔RL Climbing ★ MEMBER9 min read
58. Step 218 SafeActBench explained (arXiv:2610.07753) — tool agents fail before execution FREE6 min read
59. +97 planned

Open this genre →

1. Step 219 Paper Deep-Dive: Why Whisper Is Robust — Large-Scale Weak Supervision FREE8 min read
2. Step 220 Speech Recognition from Scratch — From Waveform to Text FREE11 min read
3. Step 221 Speech Synthesis from Scratch — From Text to a Voice FREE12 min read
4. Step 222 Representing Sound — Mel Spectrograms and Audio Tokens FREE14 min read
5. Step 223 Paper Walkthrough: SwanTale — Designing Voices from Words Alone, with Speech and Sound in One Waveform ★ MEMBER10 min read
6. Step 224 Paper Walkthrough: Interpretable MEG Decoding of Perceived Speech — Reading the Decoder's Weights as a Brain Map ★ MEMBER9 min read
7. Step 225 Paper Walkthrough: VoiceMem — A Left Brain and a Right Brain for Voice Agents, at Zero Added Latency ★ MEMBER14 min read
8. Step 226 Paper Walkthrough: Motion-Omni — Speaking and Moving in One Forward Pass ★ MEMBER12 min read
9. Step 227 Paper Walkthrough: AuK — Folding Speech Generation and Editing Into One Model ★ MEMBER9 min read
10. Step 228 Paper Walkthrough: X-AuT — Pull Audio-Encoder Layers Out Two at a Time, Then Backfill from a Bigger Teacher ★ MEMBER10 min read
11. Step 229 Paper Walkthrough: Dynamic Band Splitting — Letting Each Mixture Decide Where the Frequency Bands Go ★ MEMBER9 min read
12. +2 planned

Open this genre →

1. Step 230 RNNs and LSTMs from Scratch — Why Learn Them in the Transformer Era FREE11 min read
2. Step 231 Time-Series Forecasting from Scratch — From Classical Methods to Foundation Models FREE9 min read
3. Step 232 Do Transformers Actually Work on Time Series? — The Argument and the Practical Answer FREE11 min read
4. Step 233 Time-Series Anomaly Detection — The Math Behind the Alerts ★ MEMBER11 min read
5. Step 234 H3-World: Turning Language Understanding into World Control — Paper Explained ★ MEMBER12 min read
6. Step 235 Paper Explained: WearableQA — Testing Whether LLMs Can Reason Over 500 Days of a Real User's Wearable Data ★ MEMBER11 min read
7. Step 236 Paper Review: MetroLLM-Bench — What Happens When an LLM Runs the Ticket Machine. Why a 2.6 GB 4B Model Tied GPT-5.6, and Why Fine-Tuning Hurt at 27B ★ MEMBER13 min read
8. Step 237 Paper Explained: Video Generation Models: A Survey of Post-Training and Alignment — Four Toolboxes for Making Video Models Do What You Ask ★ MEMBER7 min read
9. Step 238 Paper Walkthrough: PointWAM — Forecasting the Scene and the Hands as 3D Point Trajectories to Teach Robot Hands from Human Video ★ MEMBER8 min read
10. Step 239 Paper Explained: STEPQuant — When and Where Quantization Errors Matter in Delta-Rule Recurrent States ★ MEMBER7 min read
11. Step 240 Paper Explained: Holi-World — Turning First-Person Recordings into a Ledger of the Room, Then Teaching a VLM to Reason over It ★ MEMBER11 min read
12. +1 planned

Open this genre →

1. Step 241 The Gemma Family from Scratch — Lineage, Inventions, and Where It Fits FREE10 min read
2. Step 242 The Llama Family from Scratch — The Main Line of Open LLMs FREE9 min read
3. Step 243 The Qwen Family from Scratch — Why It Tops Hugging Face's Download Charts ★ MEMBER7 min read
4. Step 244 The DeepSeek Family from Scratch — Breaking In with MoE and Distillation FREE9 min read
5. Step 245 The GPT Lineage — Design Thinking from GPT-1 to Today ★ MEMBER9 min read
6. Step 246 The Mistral Family from Scratch — Europe's Small-and-Strong Bet ★ MEMBER9 min read
7. Step 247 Open vs Closed — The Economics of Releasing Weights, and the Safety Argument ★ MEMBER11 min read

Open this genre →

1. Step 248 LoRA Paper Explained: Low-Rank Adaptation of Large Language Models (Hu et al., 2021) — Why Low Rank Is Enough FREE12 min read
2. Step 249 When Proxies Stop Being Good Enough — Reading August 2026's Eight Autonomous Driving Papers Together FREE13 min read
3. Step 250 Paper Deep Dive — Attention Is All You Need: What Dropping Recurrence Actually Proved FREE12 min read
4. Step 251 Mixture of Experts (MoE) from Scratch — Routing and Load Balancing in the Switch Transformer FREE9 min read
5. Step 252 Paper Walkthrough: Alpamayo — NVIDIA's Reasoning Model for Autonomous Driving FREE8 min read
6. Step 253 Symbolic vs. Connectionist — Where a 60-Year Argument Stands Today FREE12 min read
7. Step 254 Paper Walkthrough: WorldClaw — Agents That Build Walkable, Editable 3D Open Worlds from a Single Sentence ★ MEMBER11 min read
8. Step 255 Paper Deep Dive: AskChem — Changing the Unit of Search from Papers to Provenance-Carrying Claims ★ MEMBER8 min read
9. Step 256 Paper Deep Dive — Large Discovery Models: giving an LLM a value signal for what to try next ★ MEMBER13 min read
10. Step 257 Paper walkthrough: Apodex 1.1 — scaling agents around completed work ★ MEMBER11 min read
11. Step 258 Paper Walkthrough: Turning Game Development into a Verifiable Trajectory Data Engine — RLHEV and AWoMo ★ MEMBER13 min read
12. Step 259 Paper Walkthrough — J-Zero: Growing the Challenger, the Solver, and the Judge Together from Zero Data ★ MEMBER12 min read
13. Step 260 Paper Walkthrough — RoboTok: Mining the Web for Demonstrations That Move Like Yours ★ MEMBER11 min read
14. Step 261 Paper Walkthrough: CosmoH2G — Transferring a Human Hand's Flips and Rotations to a Two-Finger Gripper ★ MEMBER14 min read
15. Step 262 Paper Explained: RayOrch — Batching Children Across Parents on GPUs Without Losing Track of Who Owns What ★ MEMBER10 min read
16. Step 263 Paper Explained: False Frontiers — Diagnosing and Breaking Co-Cheating in Self-Evolving Search Agents ★ MEMBER10 min read
17. Step 264 Paper Explained: Persona Dosing — Asking an LLM for a Personality Trait by the Score ★ MEMBER6 min read
18. Step 265 Paper Explained: EVISKILL — Rewriting an Agent's Playbook from Replayable Evidence ★ MEMBER7 min read
19. Step 266 Paper Deep Dive: From Evidence to Action: How Tool-Using Agents Fail — Reading the Failure Diagnostics and Interventions ★ MEMBER7 min read
20. Step 267 Paper Explained: Refusal in Language Models Is Mediated by a Single Direction — saying "no" lives on one line inside the model ★ MEMBER9 min read
21. +10 planned

Open this genre →

1. Step 268 The Math of Distillation — Why Soft Answers Teach More FREE9 min read
2. Step 269 A Field Guide to Distillation Recipes — logit, feature, attention, self FREE9 min read
3. Step 270 Designing Distillation Data — Deciding What to Ask the Teacher FREE8 min read
4. Step 271 When Distillation Fails — Capacity Gaps and Contagious Overconfidence ★ MEMBER8 min read
5. Step 272 On-Policy Distillation — Learning From What the Student Actually Writes ★ MEMBER9 min read
6. Step 273 Distillation vs. Quantization vs. Pruning — Three Roads to a Smaller Model ★ MEMBER10 min read
7. Step 274 Distilling Agents — How to Compress a Long Trajectory ★ MEMBER11 min read
8. Step 275 Evaluating Distilled Models — Is "Close to the Teacher" a Good Metric? ★ MEMBER9 min read
9. Step 276 Build Your Own Distillation — Growing a Small Model in 100 Lines ★ MEMBER11 min read

Open this genre →

1. Step 277 LLM-as-a-Judge from Scratch — How AI Grades AI, and Where It Breaks FREE10 min read
2. Step 278 A Map of Agent Benchmarks — What SWE-bench, GAIA, and OSWorld Actually Measure FREE11 min read
3. Step 279 Self-Improving AI — Self-Play, Co-Evolution, and Generated Curricula ★ MEMBER12 min read
4. Step 280 Reward Hacking — Whatever You Measure Is Where It Breaks ★ MEMBER10 min read
5. Step 281 Benchmark Contamination — How to Doubt a High Score ★ MEMBER11 min read

Open this genre →

1. Step 282 MOSFETs from the Ground Up — A Sluice Gate Opened by Voltage, and the Reality of Leakage FREE9 min read
2. Step 283 Reading Chip Design as a Power Budget — The Physics of Leakage and Heat ★ MEMBER10 min read
3. Step 284 Band Theory from the Ground Up — Why It Had to Be Silicon FREE11 min read
4. Step 285 From FinFET to GAA — Why the Transistor Had to Go Vertical ★ MEMBER9 min read
5. Step 286 The Physics of NAND Flash — Remembering by Trapping Electrons ★ MEMBER12 min read

Open this genre →

1. Step 287 The Memory Wall from Scratch — Why Moving Data Costs More Than Computing FREE9 min read
2. Step 288 The GPU Memory Hierarchy — HBM, SRAM, Registers, and Why Movement Wins FREE9 min read
3. Step 289 CPU Pipelines and Branch Prediction — The Factory Inside One Clock Tick ★ MEMBER10 min read
4. Step 290 Systolic Arrays — Building the Heart of the TPU From Scratch ★ MEMBER10 min read
5. Step 291 Interconnects — How NVLink, PCIe, and Light Set the Limits of Scale ★ MEMBER9 min read

Open this genre →

1. Step 292 The Physics of Power — Why Lowering Voltage Pays So Much ★ MEMBER9 min read
2. Step 293 What Moore's Law Actually Says — What Ended, and What Is Still Going FREE10 min read
3. Step 294 Dark Silicon — You Can Place the Transistors, You Just Can't Light Them All FREE8 min read
4. Step 295 The Economics of Chiplets — We Split Dies Because We Cannot Build Them Big ★ MEMBER10 min read
5. Step 296 Thermal Design from Scratch — The Wall in 3D Stacking Is Heat ★ MEMBER11 min read

Open this genre →

1. Step 297 How Are Chips Made? From Silicon Wafer to Yield, Explained FREE9 min read
2. Step 298 Advanced Packaging — How CoWoS and HBM Stacking Became the Bottleneck for AI FREE10 min read
3. Step 299 EUV Lithography — The Madness of Making 13.5nm Light ★ MEMBER10 min read
4. Step 300 Yield and Design — DFM, the Art of Giving Something Up ★ MEMBER11 min read

Open this genre →

1. Step 301 How AI Accelerators Are Designed — What Actually Separates GPUs, NPUs, and TPUs ★ MEMBER8 min read
2. Step 302 How Numbers Are Represented — From FP32 to FP8 and INT4 FREE9 min read
3. Step 303 The Inference Chip Wars — Inside the Design Philosophies of Groq, Cerebras, and the LPU ★ MEMBER10 min read

Open this genre →

1. Step 304 Mapping the Semiconductor Supply Chain — From Sand to Chip, Who Holds What FREE8 min read
2. Step 305 Upstream of Semiconductors — Wafers, Photoresist, and Specialty Gases FREE13 min read
3. Step 306 Inside the Equipment Makers — What ASML, AMAT, TEL and Lam Actually Build ★ MEMBER9 min read
4. Step 307 EDA Tools from Scratch — Chips Are Written in Software ★ MEMBER10 min read
5. Step 308 IP Cores and the Fabless Model — How Arm Rules Silicon Without Making a Single Chip ★ MEMBER11 min read
6. Step 309 The Geopolitics of Chips — Export Controls and Supply Chain Rewiring, Explained Technically ★ MEMBER9 min read

Open this genre →

1. Step 310 Complexity From Scratch — What Big-O Actually Measures FREE7 min read
2. Step 311 When Big-O and Your Benchmarks Disagree — Caches, Branches, and Memory Bandwidth ★ MEMBER8 min read
3. Step 312 Randomized Algorithms — Why Rolling Dice Makes Things Faster ★ MEMBER12 min read
4. Step 313 NP-Completeness from Scratch — Not Unsolvable, but Fast to Verify FREE9 min read
5. Step 314 Approximation Algorithms — Trading Exactness for a Guarantee ★ MEMBER12 min read

Open this genre →

1. Step 315 Choosing a Data Structure — Arrays, Hashes, Trees and Heaps FREE7 min read
2. Step 316 Hashing and Nearest-Neighbor Search — The Groundwork Under Vector Search FREE9 min read
3. Step 317 Cache-Friendly Code — Why Two O(n) Loops Can Differ by 10× ★ MEMBER11 min read
4. Step 318 B-Trees and LSM-Trees — The Heart of Every Database ★ MEMBER10 min read
5. Step 319 Probabilistic Data Structures — Counting Without Counting ★ MEMBER13 min read

Open this genre →

1. Step 320 Dynamic Programming From Scratch — On Remembering Subproblems FREE8 min read
2. Step 321 Graph Algorithms from Scratch — Shortest Paths and Where They Lead FREE8 min read
3. Step 322 Linear Programming from Scratch — The Workhorse of Optimization ★ MEMBER11 min read
4. Step 323 Simulated Annealing and Genetic Algorithms — What to Do When Exact Solving Breaks Down ★ MEMBER11 min read

Open this genre →

1. Step 324 The Cost of Matrix Multiplication — Where Almost All of AI's Compute Goes FREE8 min read
2. Step 325 The FFT from Scratch — Why Convolution Turns into Multiplication ★ MEMBER9 min read
3. Step 326 Numerical Pitfalls — Cancellation, Rounding, and logsumexp ★ MEMBER10 min read
4. Step 327 How Autodiff Actually Works — Unpacking the PyTorch Magic FREE10 min read
5. Step 328 Solving Systems of Equations — Direct Methods and Iterative Methods ★ MEMBER13 min read
6. Step 329 Build Your Own Autograd — A Mini PyTorch in 100 Lines ★ MEMBER13 min read
7. Step 330 The Fourier Transform from Scratch — Reading a Signal as a Stack of Pure Tones FREE16 min read

Open this genre →

1. Step 331 Why GPUs Are Fast — The Execution Model and the Limits of Parallelism FREE10 min read
2. Step 332 Distributed Training from Scratch — Data Parallel, Model Parallel, and When Communication Becomes the Bottleneck ★ MEMBER10 min read
3. Step 333 Concurrency from Scratch — Locks, Atomics, and Memory Models ★ MEMBER9 min read

Open this genre →

1. Step 334 Linear Algebra for AI — What Vectors and Matrices Are Actually Doing FREE9 min read
2. Step 335 The Linear Algebra Under LoRA and RAG — Eigenvalues, Low Rank and Vector Search, Hands On FREE7 min read
3. Step 336 Singular Value Decomposition and Low-Rank Approximation — the Math Behind LoRA ★ MEMBER10 min read
4. Step 337 PCA from Scratch — Eigenvectors as the Axes of Your Data FREE11 min read
5. Step 338 A Tour of Matrix Decompositions — When to Reach for LU, QR, Cholesky, or SVD ★ MEMBER13 min read
6. Step 339 Tensors and Shape Manipulation — If You Can Read einsum, You Can Read Papers FREE10 min read
7. Step 340 Symmetry and Equivariance — How Group Theory Shapes Network Design ★ MEMBER10 min read

Open this genre →

1. Step 341 Calculus for AI — The Gradient Is an Arrow Saying Which Way Is Better FREE7 min read
2. Step 342 Convexity and Optimization — Why Deep Learning Works Even Though It Isn't Convex FREE9 min read
3. Step 343 Gradient Descent from Scratch — The Geometry of Learning FREE10 min read
4. Step 344 Beyond SGD — Adam, Second-Order Methods, and Constrained Optimization ★ MEMBER12 min read
5. Step 345 Matrix Calculus from Scratch — Derive the Backward Pass Yourself ★ MEMBER11 min read
6. Step 346 Jacobians and Hessians — Multivariable Calculus, Drawn ★ MEMBER11 min read
7. Step 347 Calculus of Variations — What It Means to Differentiate a Function ★ MEMBER13 min read

Open this genre →

1. Step 348 Probability and Statistics for AI — A Model's Output Is a Distribution FREE8 min read
2. Step 349 Bayes' Theorem in AI — Priors, Posteriors, and Uncertainty FREE10 min read
3. Step 350 Thinking Bayesian — A Working Feel for Priors, Likelihoods, and Posteriors ★ MEMBER11 min read
4. Step 351 Markov Chains from Scratch — The Process That Only Looks at Now ★ MEMBER11 min read
5. Step 352 A Field Guide to Probability Distributions — Where Normal, Poisson, and the Exponential Family Come From FREE13 min read
6. Step 353 Monte Carlo Methods from Scratch — Solving Integrals with Dice ★ MEMBER10 min read
7. Step 354 Hypothesis Testing and A/B Tests — How to Use a p-value, and How People Misuse It ★ MEMBER10 min read
8. Step 355 Statistical Learning Theory — Why Does Learning Generalize? ★ MEMBER11 min read
9. Step 356 Optimal Transport — The Mathematics of Moving Distributions ★ MEMBER11 min read
10. Step 357 Kernel Methods and Gaussian Processes — The Champions Before Neural Nets ★ MEMBER12 min read
11. Step 358 Bayes' Theorem from Scratch — Why a 99% Accurate Test Can Be a Coin Flip FREE16 min read

Open this genre →

1. Step 359 Information Theory and AI — Where Cross-Entropy Loss Came From FREE9 min read
2. Step 360 KL Divergence From Scratch — Measuring the Gap Between Two Distributions ★ MEMBER9 min read
3. Step 361 Entropy and Cross-Entropy — Where the Loss Function Comes From FREE9 min read
4. Step 362 Mutual Information — Putting a Number on What You Know ★ MEMBER11 min read
5. Step 363 Compression Is Prediction Is Intelligence — LLMs Through Information Theory ★ MEMBER11 min read

Open this genre →

1. Step 364 Entropy Coding from Scratch — From Huffman to Arithmetic Coding ★ MEMBER9 min read
2. Step 365 Error Correction from Scratch — Sending Data on the Assumption It Will Break FREE11 min read
3. Step 366 LDPC and Turbo Codes — The Error Correction Behind 5G and Deep Space ★ MEMBER12 min read

Open this genre →

1. Step 367 Why JPEG Degrades — The DCT and Quantization from Scratch ★ MEMBER9 min read
2. Step 368 Why PNG Does Not Degrade — Prediction Filters and Deflate FREE8 min read
3. Step 369 WebP, AVIF, JPEG XL — The Image Codec Changing of the Guard ★ MEMBER10 min read

Open this genre →

1. Step 370 Video Compression from Scratch — Motion Compensation and the GOP FREE8 min read
2. Step 371 From H.264 to AV1 — What a Codec Generation Change Really Involves FREE7 min read
3. Step 372 Motion Compensation from Scratch — Where 90% of Video Compression Happens ★ MEMBER10 min read
4. Step 373 Neural Compression — The Codec That Learns ★ MEMBER11 min read

Open this genre →

1. Step 374 Audio Compression from Scratch — The Art of Discarding What You Cannot Hear FREE8 min read
2. Step 375 MP3 and Psychoacoustics — The Science of Sounds You Cannot Hear FREE10 min read
3. Step 376 Why Opus Won — The Design of a Modern Audio Codec ★ MEMBER11 min read
4. Step 377 Neural Audio Codecs — EnCodec and the Foundation Under Speech LLMs ★ MEMBER12 min read

Open this genre →

1. Step 378 Designing a Bitrate Ladder — The First Job You Get in Streaming ★ MEMBER9 min read
2. Step 379 How to Read Encoder Settings — What CRF, Presets, and 2-Pass Actually Change ★ MEMBER7 min read
3. Step 380 HLS and DASH — How Video Actually Reaches You FREE10 min read

Open this genre →

1. Step 381 Processes and Memory from Scratch — What Is the OS Actually Protecting? FREE13 min read
2. Step 382 Containers from Scratch — What namespaces and cgroups Actually Are ★ MEMBER12 min read
3. Step 383 File Systems from Scratch — What Does "Saved" Actually Guarantee? ★ MEMBER9 min read

Open this genre →

1. Step 384 From TCP to QUIC — Reinventing Reliable Communication FREE12 min read
2. Step 385 DNS and CDNs — What Happens Between Enter and Pixels ★ MEMBER12 min read
3. Step 386 HTTP/1.1 → 2 → 3 — The Road to Multiplexing ★ MEMBER8 min read

Open this genre →

1. Step 387 Database Internals — What Happens Behind a Single Line of SQL FREE10 min read
2. Step 388 Transactions and ACID — Concurrency Hell and the Isolation Levels ★ MEMBER9 min read
3. Step 389 Distributed Databases — CAP, Replication and Consensus ★ MEMBER10 min read

Open this genre →

1. Step 390 Compilers From Scratch — How Source Becomes Machine Code FREE11 min read
2. Step 391 JIT and GC — Getting Faster While Running, Cleaning Up While Running ★ MEMBER10 min read
3. Step 392 Why Python Is Slow — Said Precisely ★ MEMBER11 min read

Open this genre →

1. Step 393 Cryptography from Scratch — Symmetric Keys, Public Keys, and Hashes FREE13 min read
2. Step 394 TLS from Scratch — Key Exchange and Certificates ★ MEMBER10 min read
3. Step 395 Authentication and Authorization — From Passwords to OAuth and Passkeys ★ MEMBER14 min read
4. Step 396 LLM Security — Prompt Injection and How to Actually Defend Against It ★ MEMBER9 min read
5. Step 397 RSA from Scratch — The Number Theory Behind Public Keys FREE20 min read

Open this genre →

1. Step 398 Serverless and Cost Design — Cloud That Won't Bankrupt You FREE10 min read
2. Step 399 Observability — Logs, Metrics, and Traces in Practice ★ MEMBER10 min read
3. Step 400 The Economics of GPU Cloud — Rent, Buy, or Commit ★ MEMBER10 min read

Open this genre →

1. Step 401 Upstream Engineering from Scratch — Why Projects Are Won or Lost at Requirements FREE9 min read
2. Step 402 The Craft of Requirements — Why "We Built Exactly What They Asked For" Fails FREE12 min read
3. Step 403 Architecture Decisions — Telling Apart What You Can Undo From What You Cannot ★ MEMBER9 min read
4. Step 404 Estimation and Scope — The Cone of Uncertainty and How to Negotiate ★ MEMBER10 min read
5. Step 405 Upstream Work in the AI Era — When Code Gets Cheap, What Gets Valuable? ★ MEMBER9 min read