‹ BackHN Continuity

Thread

Calling the AI bluff: Adding "Do not guess" cut made-up claims from 71% to 20%

96 points · 42 comments · FKJ

  1. nizarmah · · focus · HN ↗
    I mean if we can measure it, then we can probably have a way to validate it programmatically. I gave up on drawing restrictions using prompts :(
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.