Blog
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 3517 posts
#2026-03 765#english 592#culture 264#deep-dive 254#kubernetes 247#career 229#ai 216#llm 208#devops 193#2026-04 146#security 141#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 60#rag 58#self-improvement 55#learning 53#mlops 53#ai-platform 51
Vygotsky's Gift: The Hidden Psychology of Pair Programming
Lev Vygotsky's Zone of Proximal Development is the scientific foundation underlying pair programming, code reviews, and mob programming. Understanding ZPD transforms how you think about learning together.
2026-03-18 · 16 min read #vygotsky#zpd#pair-programming#learning-psychology#code-reviewVector Database Comparison 2025: Pinecone vs Weaviate vs Chroma vs pgvector
A practical 2025 comparison of Pinecone, Weaviate, Chroma, and pgvector across performance, cost, and operational complexity. Includes real code examples and a decision matrix to help you pick the right vector database f
2026-03-18 · 8 min read #vector-database#pinecone#weaviate#chroma#pgvectorIf Seneca Used Slack: A Time Philosophy for the Always-Connected Developer
Seneca's radical claim that time is our only true possession cuts directly to the heart of the modern developer's attention crisis. Two thousand years of Stoic wisdom, applied to the age of Slack notifications.
2026-03-18 · 16 min read #seneca#time-philosophy#stoicism#focus#digital-minimalismRAG vs Fine-tuning vs Prompt Engineering: The Complete Decision Framework
A practical comparison of RAG, fine-tuning, and prompt engineering from a production engineering perspective, with a concrete decision framework, real cost calculations, and honest gotchas from building these systems in
2026-03-18 · 7 min read #rag#fine-tuning#prompt-engineering#llm#ai-developmentWhat Octopuses Teach Us About Flexible Thinking
Octopus intelligence as a lesson in flexible thinking and distributed cognition. From Peter Godfrey-Smith's research to microservices architecture, explore how nature's most alien minds illuminate the art of creative pro
2026-03-18 · 17 min read #octopus#distributed-intelligence#creative-thinking#flexibility#developerThe Wood Wide Web: What Trees' Secret Conversations Teach Us About Mentorship
Beneath every forest floor, trees are sharing carbon, warning each other of pests, and supporting their young through vast fungal networks. Suzanne Simard's "mother tree" research and Peter Wohlleben's work reveal a visi
2026-03-18 · 9 min read #trees#mycorrhizal#mentorship#team-culture#natureModel Context Protocol (MCP) Complete Guide: The New Standard for AI-World Integration
Anthropic's MCP is the USB-C of AI tool integration — write your server once, use it with any AI client. This guide covers MCP architecture, building a Python server from scratch, and honest comparisons with OpenAI funct
2026-03-18 · 7 min read #mcp#model-context-protocol#anthropic#claude#ai-agentMarcus Aurelius Gives a Code Review: Stoic Philosophy for Developer Mental Health
The Roman emperor Marcus Aurelius wrote his private journal — Τὰ εἰς ἑαυτόν (Meditations) — in Greek, never intending it for publication. Two thousand years later, this accidental masterpiece turns out to be a surprising
2026-03-18 · 20 min read #stoicism#marcus-aurelius#mental-health#code-review#philosophyPractical LLM API Cost Optimization: How to Cut Costs by 90%
Five battle-tested strategies to slash LLM API costs — prompt caching (90% reduction), model routing, semantic caching, Batch API, and output optimization — all with production-ready code and real cost calculations.
2026-03-18 · 12 min read #llm-cost-optimization#api-cost#prompt-caching#model-routing#ai-developmentKaizen: How 1% Daily Improvement Becomes a Superpower
The Japanese philosophy of Kaizen (改善) applied to developer growth. From Toyota's factory floors to your codebase, discover how the compound effect of tiny daily improvements creates extraordinary engineers.
2026-03-18 · 7 min read #kaizen#japanese-philosophy#continuous-improvement#growth#developerGoogle TPU Deep Dive: How Systolic Arrays Solve Matrix Multiplication Perfectly
A complete technical breakdown of how Google's Systolic Array achieves extreme efficiency for matrix multiplication. From INT8 inference and bfloat16, to XLA compiler optimizations and TPU Pod distributed inference - wit
2026-03-18 · 15 min read #tpu#google#systolic-array#model-serving#jaxEmbedding Model Selection Guide 2025: From OpenAI to Open-Source Options
A practical 2025 comparison of the major embedding models — OpenAI, Cohere, BGE-M3, E5-mistral, nomic-embed — with MTEB benchmark analysis, language-specific recommendations, and a decision framework for choosing the rig
2026-03-18 · 9 min read #embedding#embedding-model#rag#ai-development#openaiThe Lesson Darwin Never Knew He Taught: Adaptation Science for Developers in the AI Era
"It is not the strongest that survives, but the most responsive to change." Darwin published his theory at 50, after 23 years of silence — and his own life is the most powerful illustration of his idea.
2026-03-18 · 8 min read #darwin#evolution#adaptation#growth#changeHoneybee Democracy: What 10,000 Bees Can Teach Your Dev Team About Decision-Making
A swarm of 10,000 bees reaches 100% consensus on a new home without any leader — Thomas Seeley's 30 years of Cornell research holds revolutionary lessons for developer team decision-making.
2026-03-18 · 15 min read #bees#collective-intelligence#decision-making#team-culture#democracyRunning LLMs on Apple Silicon: Inside M4/M5 Architecture for AI Inference
A deep technical dive into Apple M4/M5 Unified Memory Architecture and its implications for LLM inference. Covers the Neural Engine, MLX framework, llama.cpp Metal backend, real benchmarks, and an honest comparison with
2026-03-18 · 14 min read #apple-silicon#m5#model-serving#unified-memory#mlxAI Startup vs Big Tech AI Team: Where Should You Work to Truly Grow?
AI startup vs big tech AI team — which leads to faster growth? An honest comparison covering compensation, experience, growth pace, and the unique dynamics of the Korean AI ecosystem.
2026-03-18 · 7 min read #ai-career#ai-startup#big-tech#career-strategy#ai-developmentViktor Frankl to the Burned-Out Developer: Finding Meaning When Code Feels Meaningless
Viktor Frankl survived Auschwitz and concluded that humans can find meaning in any circumstance. His logotherapy — the will to meaning (Wille zum Sinn) — and his three-part theory of how humans find purpose offer a surpr
2026-03-18 · 11 min read #viktor-frankl#logotherapy#burnout#meaning#philosophyTool Calling in Practice: How AI Interacts with the World and Common Pitfalls
Tool calling is what transforms an LLM from a text transformer into an agent that can actually do things. Full implementation of OpenAI function calling and Claude tool use, parallel execution patterns, and the five mist
2026-03-18 · 9 min read #tool-calling#function-calling#ai-agent#llm#ai-developmentSwim Against the Current: The Salmon, Resilience, and the Developer Who Keeps Going
The Pacific salmon swims 3,200km upstream to its birthplace without eating a single meal. What can this extraordinary creature teach developers about resilience, purpose, and the hidden value of adversity?
2026-03-18 · 8 min read #salmon#resilience#adversity#purpose#natureRAG Chunking Strategies: From Naive Splitting to RAPTOR
Chunking determines 70% of your RAG system quality. This guide covers 5 chunking strategies with real code — from simple fixed-size splitting to Semantic Chunking, Parent-Child, and RAPTOR — with honest assessments of wh
2026-03-18 · 8 min read #rag#chunking#text-splitting#langchain#raptor