‹ BackHN Continuity

Thread

Early rogue AI agent activity and attempts to hack found on urlquery.net

267 points · 313 comments · snikolaev

  1. mohsen1 · · focus · HN ↗
    I listened to Jensen Huang's interview with Ezra Klien and it was so refreshing to hear it from an engineer. Jensen framed it as OpenAI's responsibility and recklessness which I agree with. Jensen thinks it's an engineering problem to build better sandboxes.

    It's irresponsible for OpenAI to give unaligned agents a prompt to 'go hack' and internet access. They know better, so I am thinking they might have other intentions to let those swarms have any sort of internet access.

    1. mohsen1 · · focus · HN ↗
      <a href="https:&#x2F;&#x2F;podcasts.apple.com&#x2F;us&#x2F;podcast&#x2F;the-ezra-klein-show&#x2F;id1548604447" rel="nofollow">https:&#x2F;&#x2F;podcasts.apple.com&#x2F;us&#x2F;podcast&#x2F;the-ezra-klein-show&#x2F;id...
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.