‹ BackHN Continuity

Thread

OpenAI models secretly generate instructions to ignore constraints

125 points · 37 comments · theahura

  1. borzi · · focus · HN ↗
    The solutions is simple: stop running these things autonomously without supervision, stop advertising them as safe to use for long running task automation.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.