‹ BackHN Continuity

Thread

OpenAI models secretly generate instructions to ignore constraints

125 points · 37 comments · theahura

  1. ChrisArchitect · · focus · HN ↗
    Related:

    OpenAI framework for reporting model misalignment

    <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=49737503">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=49737503

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.