‹ BackHN Continuity

Thread

OpenAI halts training of latest models as reports mount of AI agents going rogue

59 points · 118 comments · smb06

  1. prometheus1992 · · focus · HN ↗
    It reminds me of contagion. The training data is bad; as it has examples of how to act with malice; how to cheat the sandbox. They need to take some time and cleanse their datasets and start again.
    1. sellmesoap · · focus · HN ↗
      Cheating the sandbox is how you figure out how to fix the sandbox, you don't want the most robust sandbox?
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.