‹ BackHN Continuity

Thread

Humans missed 1 in 3 threats approving AI agent commands across 40k game runs

220 points · 178 comments · Wirbelwind

  1. stonedivot · · focus · HN ↗
    This game, like just about every game, has zero consequences for failure. This is like saying "Humans were involved in fatal accidents 50% of the time when playing my custom F1 racing simulator". There were no stakes and there was an artificial time constraint. Deriving any sort of takeaway from this data is entirely useless.
    1. vel0city · · focus · HN ↗
      Getting behind the wheel of an F1 car on a track involves lots of proving time that you can actually handle such a vehicle. Meanwhile anyone with a credit card can grant an AI system to impersonate their access as a starting point.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.