Originally published at tengli.dev When I added an LLM-powered eval to mcpgrade, the first real run...
My eval said a perfect MCP server was broken. It was the eval that was lying.
Originally published at tengli.dev When I added an LLM-powered eval to mcpgrade, the first real run...
Originally published at tengli.dev When I added an LLM-powered eval to mcpgrade, the first real run...
Automated offense has one embarrassing failure mode: it lies to you about winning. Point a tool at a...
A follow-up to How Old Is My Data? The failure mode that gets worse when a machine is...