A claim-verification layer for a local RAG co-scientist, inspired by Karpathy's llm-wiki pattern. I measured whether it catches hallucinations, almost shipped a false finding, and learned what claim-checking can and can't do.
Related
Resources for reading, tools for acting: the MCP design choice most servers get wrong
Every tool you expose over MCP ships its full definition (name, description, JSON schema) into the...
Agentic Is Powerful. The Bill Is in the Tokens.
Agentic workflows are useful. The problem is how fast tokens pile up. A single do this can turn into...
Teaching a Qwen agent to forget
Every AI photo tool today is an amnesiac critic. Lightroom edits, culling apps, and...