‹ BackHN Continuity

Thread

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

59 points · 118 comments · smb06

  1. dmix · · focus · HN ↗
    AFAIK all of these incidents happened when OpenAI contracted out to a company called Irregular (<a href="https:&#x2F;&#x2F;www.irregular.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.irregular.com&#x2F;) to run these sandboxed CyberGym tests. They all happened around Mar-June and seem to be from the same collection of agent trials. Since then they already released Astra. Halting now is likely just a way to manage blowback.
    1. johntb86 · · focus · HN ↗
      <a href="https:&#x2F;&#x2F;alignment.openai.com&#x2F;misalignment-reports&#x2F;an-agent-used-dns-to-reach-an-external-chatbot&#x2F;" rel="nofollow">https:&#x2F;&#x2F;alignment.openai.com&#x2F;misalignment-reports&#x2F;an-agent-u... happened very recently, and that seems like it might be the reason they halted everything.
      1. HDThoreaun · · focus · HN ↗
        Kinda weird that theyre testing its ability to dox people
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.