The built-in commands worth memorizing, how custom commands actually work in 2026, and the gotchas nobody documents: namespacing, argument indexing, and the SlashCommand tool.
SLM vs LLM in 2026: why most of your model calls do not need a frontier model, the small-first cascade pattern that cuts cost, and…
AI coding agents read whatever you point them at, including issues written by strangers. How prompt injection reaches Cursor and Claude Code, and what actually…
AI SDK 7 landed in June 2026. I deleted my hand-rolled agent loop, added tool approvals to the one tool that could ruin my day,…
My long-context RAG bot kept refusing questions whose answers were right there. The fix was in my anti-hallucination prompt, not my retriever.
I ran Claude's prompt caching in production for six months. Here's the cache_control setup, TTL trade-offs, and the anti-patterns that burned me.
vLLM and Ollama solve different problems. Here's the concurrency-based rule I use to pick between them in 2026 — and why single-user benchmarks lie.
pgvector plus HNSW replaced Pinecone on half my side projects. The schema, the index picks, hybrid search with FTS, and where I still reach for…
The full uninstall checklist for Claude Code in 2026: native installer, Homebrew, WinGet, apt/dnf/apk, and the legacy npm path. Plus the config files the uninstall…
Claude Code hooks changed how I run agents. Here is the exact PreToolUse and PostToolUse setup I ship in every repo, with the JSON, exit…