When LLM conversation memory accidentally becomes static analysis
Someone fed an LLM a codebase to remember, then asked questions. The model started catching bugs the author missed. Not by design, by accident.
Read the note 1 min read
From the notebook
3 notes on this topic.
Someone fed an LLM a codebase to remember, then asked questions. The model started catching bugs the author missed. Not by design, by accident.
Tailscale traced database corruption back to a WAL-mode edge case that survived billions of deployments since 2010.
A developer built a tool that lets you rewind SQLite databases to any point in their history, no external dependencies required.