‹ BackHN Continuity

Thread

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

210 points · 169 comments · Wirbelwind

  1. continuational · · focus · HN ↗
    It's kinda funny there is still software coming out whose security model is "constantly ask the user for permission, and hope they never make a mistake".

    It's been tried so many times before, and it never worked.

    1. est31 · · focus · HN ↗
      I think it's partially for responsibility reasons. Your employee approved the bash call? not our fault then!
      1. inigyou · · focus · HN ↗
        Yep and the car wasn't self-driving at the moment it crashed.
        1. autoexec · · focus · HN ↗
          ...because the self-driving feature turned itself off after detecting the crash in the fractions of a millisecond before the crash was recorded
          1. danudey · · focus · HN ↗
            "Uh oh, this is a problem. Welp, I'm outta here, good luck."
          2. Terr_ · · focus · HN ↗
            [delayed]
            1. tjoff · · focus · HN ↗
              the whole concept of having cars with that are almost capable of self-driving is utterly insane, the very least you'd need special training. We are not equipped to deal with something that works brilliantly most of the times but might kill you for no foreseeable reason.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.