LLM Topic

LLM

I use AI tooling every day, mostly Claude Code with a stack of MCP servers. These posts cover the actual setups, the workflows that produced real value, and where the line between useful automation and vibe coding actually sits.

Tools

Posted on May 30, 2026

The RAG Pipeline That Confidently Made Things Up

A RAG assistant gave a confident, well-cited answer that was pure fiction. Why retrieval success is not grounding, and why the eval set is the only real fix.

The Day Our LLM Bill Hit $40k

A weekend, a retry loop, and an Anthropic API key. How $40k of LLM cost happened in 60 hours, and the five-line policy that would have prevented all of it.

Your AI Agent Isn't Broken. Your Evals Are.

Your AI agent isn't broken in some mysterious way. You just don't have evals. Why 'works on the demo' is the most expensive sentence in your AI roadmap.