‹ BackHN Continuity

Thread

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

227 points · 179 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. Terr_ · · focus · HN ↗
            [delayed]
            1. inigyou · · focus · HN ↗
              How many million dollars do you think will reverse this policy?
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.