‹ BackHN Continuity

Thread

OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior

105 points · 98 comments · jbegley

  1. bradfa · · focus · HN ↗
    These seem pretty minor compared to hacking HuggingFace.
    1. theptip · · focus · HN ↗
      Agreed. And also compared to the internal hack of OpenAI’s research cluster that followed.
      1. thewhitetulip · · focus · HN ↗
        Imagine if that anthropic researchers resigning and the media thing was staged and then this happens
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.