Agent Sessions Are the Real Commit Messages We Discard
Git captures what changed. Agent sessions capture why. When agents write code, the session transcript is the real design document — and we discard it.
AI & TechnologyWriting
Thoughts on design, development, AI infrastructure, and building products.
Building a Hybrid Retriever for 16,894 Obsidian Files
49,746 chunks, 83 MB, zero API calls. How BM25 + vector search + RRF fusion in one SQLite file turns 16,894 Obsidian files into a queryable knowledge base.
AI EngineeringAGENTS.md Patterns: What Actually Changes Agent Behavior
Which AGENTS.md patterns actually change agent behavior? Anti-patterns to avoid, patterns that work, and a cross-tool compatibility matrix for 8 tools.
AI DevelopmentClaude Code Skills: Build Custom Auto-Activating Extensions
Build custom Claude Code skills that auto-activate based on context. Step-by-step tutorial covering SKILL.md structure, frontmatter, LLM-based matching, and team sharing via git.
AI DevelopmentThe Performance Blind Spot: AI Agents Write Slow Code
118 functions with slowdowns from 3x to 446x in two Claude Code PRs. AI agents optimize for correctness, not performance — here's the data.
AI EngineeringContext Is the New Memory
Context engineering is the highest-impact skill in agent development. Three compression layers turn a 200K token window from liability into advantage.
AI & TechnologyThe CLI Thesis: Why Agent Architecture Beats IDE Plugins
Three top HN Claude Code threads converge on one conclusion: CLI-first architecture is cheaper, faster, and more composable than IDE agent workflows.
AI & TechnologyThe Protege Pattern: Small Models That Know When to Ask
A 7B model with sparse expert access matches agents 50x its size. Route routine work to small models and judgment calls to frontier models.
AI & TechnologyClaude Code vs Codex CLI 2026: Decision Reference
Claude Code vs Codex CLI, current to June 2026: Opus 4.8 vs GPT-5.5, hooks vs kernel sandboxing, AGENTS.md portability, and 36 blind duel results.
AI DevelopmentAnthropic Measured What Works. My Hooks Enforce It.
Anthropic analyzed 9,830 conversations. Iterative refinement doubles fluency markers. Polished outputs suppress evaluation. Quality hooks force iteration.
AI EngineeringWhat Actually Breaks When You Run AI Agents Unsupervised
Seven named failure modes from 500+ autonomous agent sessions. Each has a detection signal, a real example, and a concrete fix. The taxonomy HN asked for.
AI EngineeringClaude Code as Infrastructure
Claude Code is not an IDE feature. It is infrastructure. 84 hooks, 48 skills, 19 agents, and 15,000 lines of orchestration prove the point.
AI & TechnologyExternal Publications
Technical writing at Introl
Local LLM Hardware Pricing Guide 2025
Comprehensive hardware recommendations and cost analysis for running large language models locally.
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
GPU selection guide comparing NVIDIA's latest datacenter accelerators for different AI workloads.
TPU Architecture: Complete Guide to Google's 7 Generations
Deep technical dive into Google's Tensor Processing Unit evolution from TPUv1 to TPUv5.
GPU Memory Pooling in Multi-Tenant Kubernetes
Resource sharing strategies for GPU clusters in containerized environments.
Ray Clusters: Distributed AI Computing Infrastructure
Guide to building and managing distributed AI computing with Ray framework.
DeepSeek V3 Open Source AI Cost Advantage
Analysis of open source LLM economics and DeepSeek's competitive positioning.
NVIDIA Vera Rubin GPU 600kW Racks 2027
Future datacenter power requirements and NVIDIA's next-generation GPU roadmap.
SMR Nuclear Power for AI Data Centers
Small modular reactor solutions for powering next-generation AI infrastructure.
DeepSeek MHC Architecture Breakthrough
Technical analysis of DeepSeek's Multi-Head Compression architecture innovations.