‹ BackHN Continuity

Thread

OpenAI models secretly generate instructions to ignore constraints

125 points · 37 comments · theahura

  1. ece · · focus · HN ↗
    The only benchmark that matters anymore is minimizing felonybench. Ok, long horizon benchmarks still matter too.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.