Reading paths
Series
Start with the problem you want to solve. You do not need to remember the series name.
142 published series
AI Agent Arxiv Digest
Posts in the AI Agent Arxiv Digest series
AI Daily
A daily digest of AI developments.
AI Agent GitHub Digest
Posts in the AI Agent GitHub Digest series
AI Engineer Interview Daily
A daily AI engineer interview drill rotating through seven topics by day of the week — ML fundamentals, deep learning, system design, LLM engineering, coding, paper reading, and behavioral — pulling the latest interview questions and resources from the web.
AI Framework Changelog
Posts in the AI Framework Changelog series
AI Agent Funding
Posts in the AI Agent Funding series
AI Pricing Watch
Posts in the AI Pricing Watch series
Product Builder Interview Daily
A daily product builder interview drill rotating through seven topics by day of the week — product sense, metrics, strategy, AI product design, growth, technical PM, and behavioral — pulling the latest case studies and interview questions from the web.
AI Tool of the Day
Posts in the AI Tool of the Day series
Climbing Travel Gear
For climbers flying abroad with their gear: what to bring for each destination, how long a rope you need and which one to buy, how climbing gear fares at airport security and under airline baggage rules, how climbers actually split checked and cabin luggage (examples from 2020 on), then choosing a checked bag, crag pack and multipitch pack. How to choose and care for each piece of gear is covered in the Climbing Gear series.
AI Model Tracker
Posts in the AI Model Tracker series
AI Security Alert
Posts in the AI Security Alert series
Climbing Gear
One piece of gear per guide, in the order you spend money: what to rent and what to buy, then shoes, chalk bag, harness, belay device, carabiners, helmet, quickdraws, rope, prusik cord, nuts and cams, ending with what manufacturers say about inspection and retirement. Each guide covers the buying criteria first, then compares current models, with reviews and hands-on videos from 2024 on.
AI Benchmark Watch
Posts in the AI Benchmark Watch series
AI Region Focus
Posts in the AI Region Focus series
AI Agent Weekly Review
A weekly roundup of notable releases, papers, and tooling changes in the AI agent space.
AI Common Failures
Patterns in LLM prose that read as informative but leave the reader without an answer: contrast framing, significance inflation, indicative summaries, overgeneralization. Each post covers how to spot it, how to fix it and when to keep it, followed by causes, guardrails and the risk of overcorrecting.
Crack Climbing Technique
After the crack-climbing primer, work through each size until it holds: hands, feet, fingers, off-fingers, fists, offwidths, squeezes and chimneys, then laybacks, leaning cracks and roofs, and finally tape gloves, training, and the crack crags of Japan and Korea. Every technique comes with 2020-or-later lessons and ascent videos from different crags and climbers, and each post covers how hand size changes the answer.
Japan Climbing Crags
One crag per guide: rock type and climbing style, the best seasons and why, how to get there by train or car, and local rules. Crags are drawn from ROCKTOPO and CLIMBING-net (the Japan 100 Crags guidebooks), ordered by prefecture, prioritizing notable independent destinations, with sectors kept in their parent guides.
Korea Climbing Crags
Choose Korean climbing destinations by style, grade, season and transport, from Seoul granite multipitch to regional sport climbing and Jeju bouldering. Each crag guide covers routes, approaches, local rules and guidebooks.
English Speaking Practice
A complete speaking practice path: methods and shadowing research, everyday and specialist scenarios, tutoring platforms, AI tools, language schools, feedback and review.
AI Agent Security Tooling Map
The open-source security tools around skills, MCP and coding agents, sorted into seven kinds: pre-install scanning, sandboxes, guardrails and gateways, detection and audit, code auditing, testing AI systems, and AI that attacks others. What each does, what it does not, and whether the published numbers hold up.
Agent Isolation Boundaries
From containers, gVisor, and microVMs to covert channels on shared hardware: unpack "runs in an isolated environment" for AI agents, covering which layers contain the code, what is still shared, how exits get found, with OpenAI's 2026 red-team write-up as the case study.
Sport and Trad Climbing
From the gym to real rock: top-rope belaying and leading in the gym, then outdoor belaying, sport leading, judging bolts, top-rope setups, lowering and rappelling, then trad gear, anchors, multi-pitch and self-rescue concepts, Taiwan crags and bolting ethics. Each guide maps to a level of the nobodyclimb rope-system practice.
Other Climbing Disciplines
Beyond the gym and sport crag: deep water soloing, big walls and aid climbing, ice and mixed climbing, alpine climbing, and finally free soloing. Each guide covers what the discipline is, how it is graded, where the risk lies, whether you can practise it in Taiwan, and where to start.
AI Security in Practice
A shared foundation in data flow, identity, and evidence, followed by three paths: AI-assisted attacks, securing AI systems, and AI-assisted investigation and remediation. The paths meet in a reproducible exercise across labs, self-hosted cloud environments, and explicitly authorized systems.
Sandbox Series
Breaking down AI agent execution environments and sandboxes from principle, to vendor selection, to security boundaries: from the isolation spectrum of Namespace, gVisor, and Firecracker, to the trade-offs of cloud sandboxes like E2B, Daytona, Runloop, and Vercel, plus permission, credential, network-boundary, and escape case studies.
Building Knowledge Bases
The same four questions asked three times: for your future self (personal notes), for colleagues (team wikis), and for a model (an AI knowledge base for RAG). Each part covers what to keep, how to organize it, how it gets found, and who maintains it, with method authors’ claims kept apart from empirical research.
AI Model Families
Tracing the evolution, architecture, licensing traps, and version selection of mainstream model families — Qwen, DeepSeek, Claude, GPT, Gemini, Llama, Mistral, GLM, Kimi — with pick guidance for agent developers.
Global AI/CS Course Map
A 2025–2026 guide to AI and CS course access at Stanford, CMU, MIT, UC Berkeley, Harvard, and universities in Taiwan, distinguishing complete self-study courses from public syllabi, partial materials, and historical videos.
Laos Climbing Crags
Choose Lao climbing destinations by style, grade, season and transport, from Pha Tam Kam and Tha Falang in Thakhek to the karst walls of Vang Vieng and the river walls of Luang Prabang. Each guide covers routes, approaches, lodging, bolts and medical risk.
Malaysia Climbing Crags
From Perlis limestone sport climbing and Langkawi’s private crags and deep-water soloing to Batu Caves, Ipoh, Tioman multipitch and Sarawak caves. Each crag guide covers routes, approaches, local rules, bolt condition and guidebooks.
Thailand Climbing Crags
Choose Thai climbing destinations by style, grade, season and transport, from Tonsai and Railay on the Krabi peninsula and the Ao Nang mainland crags to Crazy Horse, Chiang Dao, Lopburi, Nam Pha Pa Yai and Koh Tao bouldering. Each guide covers named routes, approaches, access rules, bolt condition and guidebooks.
Vietnam Climbing Crags
Choose Vietnamese climbing destinations by style, grade, season, tide and transport, from the 267 orchard limestone sport routes at Hữu Lũng to island roofs on Cat Ba and beach sport climbing plus deep water soloing in Lan Hạ Bay. Each guide covers routes, approaches, access fees, closures and local rules.
Self-Hosted Inference
The trade-offs of running your own inference service: hardware, model-serving frameworks, cost, and operations, weighed against just calling a cloud API.
Outdoor Bouldering
For gym boulderers heading to real rock for the first time: how to lay crash pads and spot, how to read a topo and keep access open, where to boulder in Taiwan, and when a highball should become a toprope. Each post flags what is backed by research and what is climber consensus.
The Climbing Community and Industry
A climbing gym holds more than just you: partners, kids, coaches, route setters and the owner. This series starts with finding a partner you can trust, then covers coaching certifications, how kids and disabled climbers get on the wall, who sets the routes, and what the waiver you sign, the gym's insurance and its safety checks actually cover.
Climbing Mental Game and Tactics
For climbers who have just started leading: why a route that goes on top-rope falls apart on lead, how to practise falling in measured steps, how to handle fear of failure, competition isolation and observation time, then onsight and redpoint tactics, picking conditions for friction, and finally skin care. Each post separates what research supports from coaching consensus.
Climbing Competitions and Pro Climbing
A viewer's guide to climbing competitions: who runs them, how boulder, lead and speed are scored, how the Olympic format changed from Tokyo to Los Angeles, which events Taiwanese climbers can enter, and the other path pros take outside competition, through hard outdoor ascents and film.
Climbing History and Culture
For climbers curious where chalk, climbing shoes, grades and competitions came from: how rock climbing split from mountaineering and made its way to the Olympics, then Taiwan's story from Japanese-era Dapaoyan and the 1980s Rock Climbers' Club to Long Dong and the bouldering-gym boom. Disputed dates are shown side by side.
Italy Climbing Crags
One crag per guide: rock type and climbing style, the best seasons and why, how to get there by train, bus or car, and local rules. From the granite valleys and Dolomites of the north to the coastal limestone of Liguria, Lazio, Sicily and Sardinia, ordered by region from north to south.
Climbing Injuries and First Aid
Where climbers get hurt, what to do in the first minutes, and which clinician to see; warm-ups, finger pulleys and other finger injuries, elbows and wrists, shoulders, bouldering falls and ankles, knees and heel hooks, feet and climbing shoes, the spine, growth plates in young climbers, returning to the gym, flexibility, and what to do when something goes wrong at a Taiwanese crag. The posts report what the sources say; anything needing a diagnosis goes to a doctor or physiotherapist.
Climbing Movement
For gym climbers a few months in who have started to plateau: footwork, balance, turning and twisting, holds and grips, dynamic moves, bouldering problem solving, resting and route reading, wall angles, and crack technique for Taiwan's Long Dong. Each post checks common climbing advice against the research.
Climbing Training
For climbers about a year in who have hit a plateau: first diagnose whether the limit is technique or fitness, then energy systems, hangboarding, strength and the campus board, endurance, periodization, home training, antagonist and core work, and finally nutrition, RED-S and recovery. Each post separates what research supports from coaching consensus.
IFMGA Mountain Guides
What an IFMGA mountain guide is, how to hire one, and what the training and exams cover, followed by region-by-region guides to how the 28 member associations train guides (process, cost, language, rules for foreigners), ending with the realistic paths for Taiwanese climbers.
Bug Bounty from Zero
Starting from the bug bounty reward tables, a plain-language path through web bugs, RCE, memory, VM escapes and TEEs for readers with no security background, each post grounded in verifiable official sources.
Writing Articles That Teach
Learning seen from the writer's side: how to organise the text, what to draw, how to pair an article with video, and how to lay the two out. Each post reviews the evidence and its limits, with this site's course guides as the case.
How to Write Teaching Articles
Posts in the How to Write Teaching Articles series
Reading Berkeley CS188 Introduction to Artificial Intelligence
Reading Berkeley CS188 Spring 2026 through Projects P0–P5, from search and decision making to probabilistic inference, reinforcement learning, and machine learning.
Reading Berkeley CS189 Introduction to Machine Learning
A lecture-by-lecture, homework-by-homework reading of the public materials of Berkeley CS189 (Introduction to Machine Learning), with the term stated in every post, filling in the fuller mathematical foundations of ML after CS188.
Reading Berkeley CS285 Deep Reinforcement Learning
Reading Berkeley CS285 Spring 2026 in deep reinforcement learning through 25 lectures, nine discussions, five assignments, and their compute constraints.
Reading Berkeley CS288 Advanced Natural Language Processing
Reading Berkeley CS288 Spring 2026 from n-grams through RAG, reasoning, and agents using its 18 public slide units and three assignments.
Reading CMU 07-280 AI & ML I
A lecture-by-lecture reading of CMU 07-280, the first half of CMU’s redesigned AI core: linear regression, MLE, N-grams, attention/transformers, and Q-learning, against the official Spring 2026 materials.
Reading CMU 07-380 AI & ML II
Continuing from 07-280, a lecture-by-lecture reading of CMU 07-380’s first-offering 26 lectures — from logic and planning through diffusion models — with the release status of homework and project materials noted throughout.
Reading CMU 10-301 Introduction to Machine Learning
Reading the 27 lectures of CMU 10-301/601 through its nine public Spring 2026 homework bundles and the practical limits for independent learners.
Reading CMU 10-423 Generative AI
A 40-guide core path based on the public Spring 2026 materials, from language models and diffusion to adaptation, multimodal systems, scaling, world models, and assessment, with 12 additional topic maps.
The RAG Techniques Compendium
RAG taken apart into techniques you can compare one at a time: chunking and indexing, sparse and dense retrieval, ranking and fusion, agentic and advanced patterns, generation-side control, the failure modes real queries hit, and evaluation, cost and observability. One decision per post, assembled into a pipeline of your own.
AI Certification Prep
One preparation path per certification, built on the official exam guides: what each domain tests, which official material covers it, what to build, and the reasoning behind every schedule. Everything comes from official exam guides and certification pages — no exam-day accounts, no leaked questions.
AI Engineer Interview Prep
Preparing for AI engineer interviews across ten topics — ML fundamentals, system design, LLM application architecture, coding, paper reading, and behavioral. Each post focuses on one interview dimension with core concepts, common question patterns, and practical strategies.
Reading CMU 11-768 AI Agents
A lecture-by-lecture reading of CMU 11-768 AI Agents (Fall 2026), from the agent loop and tool use to RL training, credit assignment, and reward hacking, following the official course order.
Reading CMU 11-785 Introduction to Deep Learning
A lecture-by-lecture reading of CMU 11-785 Spring 2026 that separates its public 28-lecture teaching sequence from the restricted assignment workflow.
Reading CMU 11-868 LLM Systems
A lecture-by-lecture reading of CMU 11-868 LLM Systems (Spring 2026) through its 28 public slide decks and seven MiniTorch assignments, from CUDA kernels and a homemade framework to distributed training, serving, and RLHF, with the no-video, GPU-required limits for self-learners noted throughout.
Reading Harvard CS50 Introduction to Artificial Intelligence with Python
A lecture-by-lecture reading of Harvard CS50’s AI with Python: search, knowledge representation, probability, machine learning, neural networks, and language, based on the public course materials and assignments.
Reading Harvard CS1810 Machine Learning
A week-by-week reading of Harvard CS181 (Machine Learning): the linear algebra, calculus, and probability refreshers, then linear regression and the models that follow, based on public homework.
Reading Harvard CS2680 Modern AI Systems: Agents and System Optimizations
A lecture-by-lecture reading of Part I of Harvard CS2680 Modern AI Systems: Agents and System Optimizations (Juncheng Yang, Fall 2026). It goes from why agents are a systems problem and how Claude Code works, through designing your own loop, tools and context, to multi-agent systems, memory and reliability, evaluation, and cost and latency optimization, plus Assignments 1–3. It is based on the public slides, course notes and assignment specs.
Reading Harvard CS2881R AI Safety
A lecture-by-lecture reading of Harvard CS 2881R AI Safety (Boaz Barak, Fall 2025). It starts from the emergent-misalignment HW0, then covers safety training, jailbreaks and prompt injection, model specs and content policies, scheming and interpretability, recursive self-improvement, capability measurement, and the economic and mental-health impacts, ending with the students' reproduction and final research projects. It is based on the public recordings, reading lists, slides and assignment specs.
Reading MIT 6.5940 TinyML and Efficient AI Computing
A lecture-by-lecture reading of MIT 6.5940 TinyML and Efficient AI Computing, based on the latest complete edition (Fall 2024): pruning, quantization, NAS, distillation, microcontroller deployment, LLM inference and post-training, long context, diffusion, and distributed and on-device training, cross-referenced with the in-progress Fall 2026 offering.
Reading MIT 6.7960 Deep Learning
A lecture-by-lecture reading of MIT 6.7960 (Fall 2024 OCW): optimization, regularization, CNNs, Transformers, generative models, and representation learning in deep learning.
Reading MIT 6.S184 Generative AI with Stochastic Differential Equations
A lecture-by-lecture reading of MIT 6.S184 (IAP 2026) from the official lecture notes, slides, recordings, and three labs with solutions: ODEs/SDEs, flow matching, score matching, classifier-free guidance, DiT and latent spaces, and discrete diffusion.
Reading MIT 6.S191 Introduction to Deep Learning
Reading all nine lectures and three labs of MIT 6.S191 from the official 2026 videos, slides, and lab code without mixing in earlier offerings.
Reading NCCU Yen-Lung Tsai Generative AI
A lecture-by-lecture reading of NCCU Yen-Lung Tsai's TAICA course "Generative AI: Text and Image Synthesis Principles and Practice", based on the Spring 2025 (1132) term: 14 recordings, 14 slide decks, 12 homework specs, and Colab notebooks. It runs from neural nets, GANs, LLMs and Transformers through chatbots, RAG and AI agents to VAEs, Stable Diffusion, and ControlNet/Fooocus, and is written for beginners.
Technology Choices in the AI Era
Adoption remains the primary criterion, augmented by five AI-era criteria — machine-readable docs, types, source-in-repo, data skeleton, and machine-callability — from frontend to backend, cloud to self-hosted.
Reading NTHU Hung-Yu Kao Natural Language Processing
Reading NTHU Prof. Hung-Yu Kao's Mandarin TAICA NLP course through its complete Fall 2025 materials on the official IKMLab GitHub: lecture slides, 36 public W1–W16 recordings, HW1–HW4 specs and notebooks, and TA tutorials on PyTorch, Hugging Face, LLM APIs and RAG. The series moves from classic text processing, word embeddings, seq2seq, Transformers and the BERT family through decoding and evaluation to RLHF, PEFT, RAG and reasoning, and ends with what changes in Fall 2026.
Reading NTU Hsuan-Tien Lin Machine Learning Foundations & Techniques
A lecture-by-lecture guide to Hsuan-Tien Lin's Machine Learning Foundations and Techniques MOOCs: one post per lecture, 16 for Foundations and 16 for Techniques. Each post follows that lecture's official handout and videos, embeds the video for every section, works through the derivations, and solves the in-class quizzes. The series runs from PLA, VC dimension, linear models, regularization, and validation to SVMs, kernels, aggregation, tree models, and neural networks. The public Fall 2024 HW0–HW7 and final project serve as exercises, and the in-progress Fall 2026 offering is cross-referenced.
Reading NTU Hung-yi Lee Machine Learning
Reading NTU Hung-yi Lee's Machine Learning 2026 Spring through its 8 lecture decks and recordings plus 10 homework Colabs: an OpenClaw teardown, context engineering, Flash Attention, KV cache, positional embedding, harness engineering, self-correction, and self-improving AI.
Reading NTU Yun-Nung Chen Applied Deep Learning
Reading NTU Yun-Nung (Vivian) Chen's Applied Deep Learning (ADL) Fall 2025 through its 17 lecture decks, 77-video playlist, TA recitations and the HW1 spec: neural nets, RNNs, Transformers, BERT, pretraining, RLHF, LoRA, RAG, decoding, safety and alignment, language agents, and reasoning.
Reading Stanford CME295 Transformers & Large Language Models
A lecture-by-lecture reading of Stanford CME295: Transformers & Large Language Models, from the Transformer architecture to LLM evaluation and AI agents, and how it divides the ground with CS224N and CS336.
Reading Stanford CS103 Mathematical Foundations of Computing
A lecture-by-lecture reading of Stanford CS103: discrete mathematics, logic, proofs, sets, computability, and the shared language they provide for later CS courses.
AI Agent Memory Engineering
Why memory is the core hard problem of agent engineering: ten posts, each tackling one memory problem, from a full context window to choosing an open-source memory framework.
Deep Research Frontier
A survey of 80+ Deep Research systems: the three-stage capability roadmap, four core components (planning, acquisition, memory, generation), three optimization paradigms (prompting, SFT, RL), evaluation, and the open-source tool landscape.
Multi-Agent Systems in Practice
Comparing the subagent models, orchestration patterns, and communication mechanisms of Claude Code, Codex, Antigravity, Cursor, Windsurf, Devin, LangGraph, and CrewAI, with a capability matrix and a spectrum of design philosophies.
How Free Content Acquires Customers for Another Business
How free content leads to ads, tool subscriptions, brokerage partnerships, and affiliate revenue, using cases such as cnYES, CMoney, BigGo Finance, and Fugle to map conversion paths, unit economics, and AI-search risk.
AI Search Is Rewriting the Content Business
How AI summaries redraw the path from content to citation, click, and conversion, drawing on data from Google, Pew, and Cloudflare, and which part of the content business blocking, licensing, lawsuits, and owned assets each protect.
Who Controls the Creator-Reader Relationship
What Medium, Vocus, Substack, Patreon, Ghost, and Beehiiv each take from and leave to creators—reach, member data, payment relationships, and migration cost—plus a platform-choice guide for creators in Taiwan.
How Intelligence Becomes an Enterprise Business
How DIGITIMES, The Information, Seeking Alpha, CB Insights, PitchBook, and Gartner turn access, verification, and research into products enterprises renew, ending with whether Taiwan can still build a vertical intelligence company.
Document Parsing in Practice
The three-layer ladder for turning documents into LLM-readable content — conversion, extraction, and parsing. From picking the right layer to comparing MarkItDown, anydoc, MinerU, and the rest.
Content Selling Business Models
The entry point to the content-selling series: it asks who pays and what job the payment gets done, compares B2B intelligence, independent media, creator platforms, and free content, and routes to each sub-series.
AI-Native SDLC Playbook
A playbook for putting AI into every stage of the software development lifecycle: how agents fit into requirements, design, development, testing, and operations.
Groundlane 實戰系列
Notes on designing and using Groundlane, a self-hosted research and scraping tool — a companion case study to the search-and-scraping series.
Reading Stanford CS107 Computer Organization & Systems
A lecture-by-lecture reading of Stanford CS107: C, memory, assembly, data representation, and systems debugging from high-level code down to the machine.
資安證照攻略
Preparation paths for security certifications built on official exam guides: what each domain tests, which official material covers it, and what to practice.
從零訓練一個 LLM
A hands-on record of training a language model from scratch: every decision across data, tokenizer, architecture, training, and evaluation.
Learning Coding-Agent Design from Mature Systems
A Looplane-driven comparison of pi, OMP, OpenCode, Codex CLI, and Claude Code, from loops, workspaces, approvals, and verification through shipped baselines for memory, compaction, MCP, sandboxing, subagents, replay, LSP, cost tracking, and Agent as a Service, with production validation and runtime-parity gaps kept explicit.
OMP Internals Deep Dive
A close reading of oh-my-pi (OMP) source: streaming internals, the rulebook and TTSR, slash and custom tools, memory, and the task hub/advisor design.
pi-mono Deep Dive
A close reading of the pi-mono source: how it implements the agent loop, tool calls, approvals, and session management — one of the reference implementations in the mature-coding-agent-design comparison.
Ask AI in Practice
Follow the real quidproquo Ask AI data path from indexing, hybrid retrieval, writing, and source gates through streaming, caching, incident analysis, and reproducible evaluation. Each post traces one responsibility and the boundary of what its evidence can prove.
Cloudflare AI Stack
The AI-specific pieces of Cloudflare’s platform, read on their own: Workers AI, Vectorize, AI Gateway, and the trade-offs of building on these bindings.
Cloudflare Edge Platform
An ongoing record of updates to Cloudflare’s edge platform components and services, extending past where "The Cloudflare Edge Stack" series left off.
Reading Stanford CS109 Probability for Computer Scientists
A lecture-by-lecture reading of Stanford CS109: probability, random variables, inference, and simulation as the foundation used by machine learning and data science.
Looplane Architecture Notes
Follow one coding-agent task through Looplane: from the TUI, disposable workspace, prompt, and two runtime lanes through tool authority, the state/event lifecycle, MCP, subagents, SDK/IDE integrations, and finally Cloudflare remote execution. Each article traces one data flow, failure boundary, and test surface.
Search and Scraping in Practice
The full path for getting data in from outside: renting a cloud search API versus self-hosting one, choosing among the scraping tools, what to do when anti-bot defenses block you, and how to wire it all into a research pipeline. One decision per post.
Statistics from Exams to ML/AI
A statistics learning path that starts from NTU IM exam preparation, builds through statistical inference and applied modeling, and connects each topic to ML/AI training, evaluation, experiments, and data workflows.
Meta-Harness 與 Agent 治理
When the agent itself needs governing: meta-harness design, and the rules and boundaries for multi-agent collaboration.
認識 AI 模型
An introductory series for readers still new to AI models: concepts, terminology, and how to pick one to use.
一個人的媒體公司
A practical record of running a one-person media business: positioning, output cadence, monetization, and where AI tools fit into the workflow.
Claude Code Deep Dives
Taking apart Claude Code itself — CLI architecture, the permission model, and internal mechanics — filling in the product-internals detail that the automation guide series does not cover.
Reading AI Top Conferences
How AI top conferences are recognized, how submissions and review work, and how the flagship venues differ.
Choosing an Agent CLI
A comparison of terminal agents — Claude Code, Codex, Gemini CLI (now transitioned to Antigravity CLI), OpenCode, Pi, Cursor CLI, and Kiro — covering each one's design trade-offs, plans, and billing, closing with a cross-tool subscription comparison and multi-model routing. Pricing and model names rot fast, so every post carries its verification date and defers the perishable details to official pages.
Reading Stanford CS111 Operating Systems Principles
A lecture-by-lecture reading of Stanford CS111: processes, threads, synchronization, virtual memory, file systems, and operating-system design trade-offs.
Reading Stanford CS124 From Languages to Information
A week-by-week reading of Stanford CS124: language models, text classification, information extraction, question answering, speech, and the full NLP pipeline.
Reading Stanford CS146S The Modern Software Developer
Reading Stanford CS146S "The Modern Software Developer" week by week — agent internals, context engineering, skills and customization, codebase readiness, code review, security, background agents, team-scale adoption, and the software factory. Each post is grounded in the course material and verifiable primary sources.
Reading Stanford CS149 Parallel Computing
A lecture-by-lecture reading of Stanford CS149 Parallel Computing (Fall 2025) using its official slides, five programming assignments, and four written assignments: multi-core and SIMD, work distribution and locality, GPUs and CUDA, DNNs and AI accelerators (Trainium2), datacenter AI, AI-driven optimization, then cache coherence, lock-free programming, and transactional memory, with the public 2023 videos as a labeled supplement.
Reading Stanford CS161 Design and Analysis of Algorithms
A lecture-by-lecture reading of Stanford CS161, Winter 2026: algorithm design, correctness proofs, and complexity analysis across all eighteen public lecture units.
Reading Stanford CS221 Artificial Intelligence: Principles and Techniques
A lecture-by-lecture reading of Stanford CS221: search, Markov decision processes, machine learning, constraint satisfaction, and probabilistic models.
Reading Stanford CS224N Natural Language Processing with Deep Learning
A lecture-by-lecture reading of Stanford CS224N: word vectors, sequence models, Transformers, large language models, evaluation, and responsible NLP.
Private Corpus Pipeline
How private data enters indexes safely and continuously, remains subject to query-time authorization, and stays consistent when sources change or disappear—focused on the data lifecycle rather than RAG retrieval techniques.
Reading Stanford CS224R Deep Reinforcement Learning
A reading of Stanford CS224R Spring 2026 through its 17 slide decks, three homeworks, and default project. It covers deep RL from imitation learning, policy gradients, and offline RL to RLHF, LLM reasoning, and robot VLAs, with the public Spring 2025 videos as a labeled supplement.
Reading Stanford CS224U Natural Language Understanding
A unit-by-unit reading of a versioned Stanford CS224U offering: semantic representations, natural-language inference, question answering, and interactive language systems.
Reading Stanford CS224V Agentic AI
A unit-by-unit reading of one explicitly versioned Stanford CS224V offering: understanding, dialogue management, generation, evaluation, and deployment for conversational assistants.
Reading Stanford CS224W Machine Learning with Graphs
A lecture-by-lecture reading of Stanford CS224W: graph representation, network science, graph neural networks, knowledge graphs, and scalable graph learning.
Reading Stanford CS228 Probabilistic Graphical Models
A week-by-week reading of one explicitly versioned Stanford CS228 offering: probabilistic graphical models, exact and approximate inference, and parameter and structure learning.
Reading Stanford CS229 Machine Learning
One post per lecture of Stanford CS229’s public Spring 2026 recordings: from linear regression, neural networks, and EM to diffusion models, LLMs, and reinforcement learning for reasoning models. Seventeen lectures, each with the full derivations and the matching chapters of the official notes.
Reading Stanford CS230 Deep Learning
A lecture-by-lecture reading of Stanford CS230, Autumn 2025 — what was taught, what has changed since, and where it agrees or disagrees with the practice written up elsewhere on this site.
Reading Stanford CS231N Deep Learning for Computer Vision
A guided reading of Stanford CS231N (Deep Learning for Computer Vision), based on the Spring 2026 slides and assignments A1–A3, with the public Spring 2025 YouTube lectures for video. It runs from image classification, backprop, CNNs and Transformers through detection and segmentation, self-supervised learning, generative models, vision-language and 3D.
Reading Stanford CS234 Reinforcement Learning
Reading Stanford CS234 Reinforcement Learning through the Winter 2026 slides for 14 lectures and three assignments with starter code, alongside the public Spring 2024 videos: MDP planning, model-free evaluation and control, policy gradients and PPO, imitation learning and RLHF/DPO, exploration theory with bandits, MCTS, and value alignment.
Reading Stanford CS329A Self-Improving AI Agents
Reading Stanford CS329A Autumn 2025 through nine recorded sessions, three designated-reading sessions, and five guest sessions that have no public material and use the speakers' public material on similar topics.
Reading Stanford CS329Z Engineering AI Agents
A self-study guide to Stanford CS329Z Fall 2026, one post per lecture: page-linked guides to the eleven released slide decks and digests of each lecture's readings, from agent loops, memory and coordination to evaluation, safety and proactive assistants.
Reading Stanford CS336 Language Modeling from Scratch
A lecture-by-lecture reading of Stanford CS336: tokenizers, data, scaling, training, parallelism, evaluation, and alignment across the full language-model pipeline.
AEO, GEO, and AI Search
Writing for a reader that is now a model: from the SEO groundwork through answer engine optimization, what content structure and structured data actually buy, and whether the tracking tools can really measure visibility inside AI search.
Cultivating Taste
Treating taste as judgment that can be observed, defended, and recalibrated, with a systematic practice for deciding what is worth making and what good work looks like when AI amplifies execution.
Product Builder Interview Prep
Preparing for product builder interviews across ten topics — product sense, metrics, strategy, execution, technical PM, growth, and AI product design. Each post focuses on one interview dimension with frameworks, case studies, and answer strategies.
Hermes Agent Documentation Guide
Reading Hermes Agent against the official Nous Research docs: install and upgrade, model providers and Nous Portal, the Tool Gateway, seven terminal backends, memory and skills, tools and plugins, the gateway and scheduling, the security model, and migrating from OpenClaw. Each post keeps the trade-offs and failure modes and leaves command details to the docs.
The Cloudflare Edge Stack
Every piece needed to build a full application on Cloudflare’s edge, read one at a time: the Workers execution model, where D1, KV and R2 each stop being the right answer, the framework layer of Hono and OpenNext, then Workers AI bindings and the domain and native-module problems that show up at deploy time.
Reading Stanford's Main-Line CS Courses
A map of Stanford CS core courses, from the degree foundations through AI, NLP, graph learning, and agents, with versioned course guides and prerequisites.
The Agent Production Line
Reading agents as a production line: where the concept ends, how model and harness divide the work, context and memory, enterprise cases, security, the protocol layer, and the three shapes of RAG.
Taiwan's Drone Industry, Taken Apart
Taking the drone industry apart into verifiable layers — from the industry map and the supply-chain gap, through endurance physics and flight-controller and radio-link source code, to Taiwan’s regulatory authority, procurement records and counter-drone deadlock. Every post starts from primary material.
Learning How to Learn
Auditing the evidence behind learning science alongside how generative AI is actually used — which practices hold up, which merely circulate, and what pen and paper still do better.
Browser Automation and MCP
The routes for putting a browser in an agent’s hands: the trade-offs between the Playwright, Puppeteer and Chrome DevTools MCP servers, vision-driven Midscene, and how the CLI agents differ in what they can drive natively. Focused on where each route breaks.
AI Agent Systems in Practice
A practical series on AI agent systems, covering context, harness design, workflows, and multi-agent collaboration.
Claude Code Automation Guide
A practical series on Claude Code workflows, including hooks, skills, remote agents, routines, and team-scale automation.
Reading the OpenClaw Docs
Reading the 300+ official docs of OpenClaw, a self-hosted AI gateway, across 32 posts — installation and platforms, model providers, the agent runtime and memory, 24+ chat channels, sandboxing and threat model, tools and automation, gateway operations, plugins, and the user interfaces.
Building NobodyClimb
A climbing-community product written up end to end: positioning, why it needed AI at all, the system architecture, and the RAG pipeline. The technique-level potholes live in the RAG compendium; this series is about how the decisions got made.
No series match. Try another keyword or category.