Thread

Nvidia wants to put a watchdog chip next to every AI agent

230 points · 299 comments · jonbaer

tantalor · 1790626819 · focus · HN ↗
What happens when we're overrun by lizards?
> No problem. We simply unleash wave after wave of Chinese needle snakes. They'll wipe out the lizards.
But aren't the snakes even worse?
> Yes, but we're prepared for that. We've lined up a fabulous type of gorilla that thrives on snake meat.
But then we're stuck with gorillas!
> No, that's the beautiful part. When wintertime rolls around, the gorillas simply freeze to death.
1. ArcHound · 1790627223 · focus · HN ↗
  I worry that the AI companies put less effort into a mitigation strategy than you did.
  1. Joel_Mckay · 1790628926 · focus · HN ↗
    There is a difference between risk mitigation, and remote administration tools. The risk of stealing from competitors with a backplane monitoring system may not end up forming the desired control asymmetry.
    The hidden agent risk in LLM often can't be detected during training and evaluation. =3
    <a href="https://www.youtube.com/watch?v=wL22URoMZjo" rel="nofollow">https://www.youtube.com/watch?v=wL22URoMZjo
    <a href="https://www.youtube.com/watch?v=JAcwtV_bFp4" rel="nofollow">https://www.youtube.com/watch?v=JAcwtV_bFp4

Unofficial Hacker News client; not affiliated with Y Combinator.