Blog

#2026-03 765#english 592#culture 264#deep-dive 254#kubernetes 249#career 229#ai 219#llm 209#devops 196#2026-04 146#security 143#database 114#observability 113#communication 109#history 107#architecture 100#productivity 96#finance 88#economy 84#mindset 81#psychology 80#ai-papers 79#food 78#it 78#travel 78#deep-learning 77#japanese 77#networking 77#performance 72#business-travel 70#linux 70#gpu 69#ai-agent 66#cs-fundamentals 63#postgresql 61#rag 58#self-improvement 55#learning 53#mlops 53#python 52

• From Documents to a Knowledge Graph: An Honest Pipeline

  'Extract a knowledge graph from your documents' looks like a single LLM call in a demo. But turning a customer's documents into a graph you can actually query is a six-stage pipeline, and most of the cost and pain lives

  2026-07-15 · 10 min read #knowledge-graph#ai#llm#data-engineering

• A Map of Knowledge Graph Tools and Frameworks: What to Pick, When

  Graph databases, the RDF and ontology stack, and graph RAG frameworks have exploded over the last two years. Link lists are already abundant, so this post draws an honestly-opinionated map instead. For each category: wha

  2026-07-15 · 9 min read #tools#knowledge-graph#graph-rag#ontology#frameworks

• Turning a Customer Domain Into a Model — From Ubiquitous Language to Ontology

  A customer's domain knowledge usually lives not in documents but as tacit knowledge inside people's heads. One core job of a Forward Deployed Engineer is turning that scattered tacit knowledge into an explicit model the

  2026-07-15 · 11 min read #ontology#knowledge-graph#domain-driven-design#architecture#forward-deployed-engineer

• Graph RAG, Explained: What It Is and When It Earns Its Cost

  The standard RAG recipe — chunk, embed, retrieve top-k — works when the answer sits inside a single chunk, but it stalls structurally on multi-hop questions and on global sensemaking questions that span the whole corpus

  2026-07-15 · 8 min read #rag#graph-rag#knowledge-graph#ai#llm

• Five Habits for Working Well with AI Coding Tools

  The same tool produced a 55.8% gain in one experiment and a 19% loss in another. What flipped the sign was not the tool, but how it was used. Five habits drawn from METR, the GitHub Copilot RCT, the Stack Overflow survey

  2026-07-12 · 10 min read #ai#productivity#software-engineering#developer-experience

• What to Learn Deeply, What to Skim — A Learning Strategy for the AI Era

  When an AI answers almost anything in three seconds, what is still worth learning deeply? Cognitive psychology has an uncomfortable answer: memory is built by pulling information out of your own head, not by having it ha

  2026-07-12 · 12 min read #career#learning#ai#software-engineering

• From Senior to Staff: What Actually Gets Evaluated

  Plenty of engineers believe that shipping more, faster, is the path to promotion. But open an actual public engineering ladder — Dropbox, CircleCI, Rent the Runway — and there is no axis called output. There is scope, co

  2026-07-12 · 12 min read #career#software-engineering#growth#staff-engineer

• When Code Generation Gets Cheap, Which Skills Go Up in Value — What Depreciates and What Appreciates

  When code generation becomes cheap and abundant, value does not vanish — it moves to whatever is still a bottleneck. Right now that bottleneck is verification, judgment, and integration. Building on Jason Wei's asymmetry

  2026-07-12 · 14 min read #career#software-engineering#ai#skills#code-review

• Does AI Actually Make Developers Faster? What the Measured Numbers Say ♪ Listenable

  Two randomized controlled trials reached opposite conclusions. One found developers using AI were 55.8% faster. The other found they were 19% slower. But METR, who produced the second number, published a follow-up in Feb

  2026-07-12 · 18 min read #career#ai#productivity#software-engineering#developer-experience

• The 2026 Developer Job Market — What the Data Shows, and What It Does Not

  It feels like the worst market in a decade, yet BLS projects 15% growth over ten years. Both are true. I pulled the raw Indeed postings index (Feb 2020 = 100, peak 233.87 in Feb 2022, 72.51 in June 2026), layoffs.fyi (12

  2026-07-12 · 9 min read #career#job-market#software-engineering#hiring

• Assembling and running an engine in a browser tab — a look at Combustion Lab

  Combustion Lab (combustionlab.net) lets you assemble an internal combustion engine and run it crank-angle by crank-angle, right in a browser tab, no install required. It shows the intake, compression, combustion, and exh

  2026-07-11 · 6 min read #simulation#thermodynamics#webassembly#physics#engine

• Tencent Hy3: reading a 295B open-weight MoE without the hype

  On July 6, 2026, Tencent released Hy3 under Apache 2.0: a Mixture-of-Experts reasoning and agent model with 295B total parameters but only 21B active per token. Here is what is genuinely new, where it sits in the Chinese

  2026-07-11 · 5 min read #hy3#tencent#hunyuan#open-weights#moe

• Running Small Models Hands-On with a Single RTX 5090 — microGPT, OCR, Music Generation

  I SSHed into a single RTX 5090 (Blackwell, 32GB) and ran a trio of small models by hand. I trained a char-level GPT from scratch in 28 seconds (10.75M parameters, 1.17M tokens/s), pitted a dedicated OCR model (TrOCR) aga

  2026-07-11 · 8 min read #pytorch#gpu#llm#ocr#hands-on

• What a Good Agent Benchmark Looks Like in 2026 — UniClawBench, Live Containers, and a Hidden Supervisor

  UniClawBench, posted to arXiv in July 2026 by HKU MMLab, is a self-described capability-driven benchmark for proactive agents. Instead of matching against static, pre-recorded answers, it runs agents inside live Docker c

  2026-07-11 · 5 min read #ai#agents#evaluation#benchmark#llm

• VO2 Max and Longevity — What 122,007 People Actually Tell Us

  Cardiorespiratory fitness, often summarized as VO2 max, is one of the markers most strongly associated with how long people live. In a 2018 Cleveland Clinic study that tracked 122,007 adults, higher fitness went with low

  2026-07-11 · 6 min read #fitness#health#longevity#vo2max#science

• Why Scarf Reluctantly Left Haskell After 7 Years — The Real Cost of a Language Choice

  Scarf is moving its backend off Haskell to Python after seven years in production. The interesting part is why. Founder Avi Press readily admits Haskell kept most of its promises — reliability, type safety, performance —

  2026-07-11 · 7 min read #haskell#python#engineering-decisions#compile-times#ai-assisted-development

• Tesla's FSD v14 Lite Reaches Korea — Distilling a Model onto Old Hardware, and the Honest Meaning of 'Supervised'

  On July 10, 2026, Tesla Korea began rolling out FSD (Supervised) v14 Lite. It goes only to US-built Model 3 and Model Y cars running the older HW3 computer. This post explains why 'Lite' is not a marketing tier but the r

  2026-07-11 · 6 min read #tesla#fsd#autonomous-driving#adas#hw3

• Why RLHF Models Game Their Rewards — The Mechanisms, Symptoms, and Mitigations of Reward Hacking

  "Reward Hacking in the Era of Large Models," posted to arXiv in April 2026 by Xiaohua Wang and 22 co-authors, is a survey of why and how RLHF-aligned large models game their reward signals. Its central proposal is the Pr

  2026-07-11 · 5 min read #ai#llm#alignment#rlhf#safety

• tts-bench: comparing local TTS models when quality is subjective

  tts-bench is a local benchmark by 5uck1ess for comparing 55 text-to-speech models on hardware you own. It splits evaluation into three lenses: Speed (TTFA, RTF, memory), Listen (every model on every prompt, judged by ear

  2026-07-11 · 5 min read #tts#text-to-speech#benchmark#local-ai#evaluation

• pgrust: Postgres Rewritten in Rust, Passing 100% of the Regression Tests — What That Actually Means

  Malcolm Matis (malisper) released pgrust, a rewrite of Postgres in Rust. It targets Postgres 18.3 compatibility, passes more than 46,000 regression queries, and boots from an existing 18.3 data directory. This piece is a

  2026-07-11 · 6 min read #postgresql#rust#pgrust#database#regression-tests