‹ BackHN Continuity

Thread

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

208 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. jstummbillig · · focus · HN ↗
      The difference being, that this time it's (at this point: obviously, but previously much debated) a gapfill. I think it worked out quite well for us, to add some friction and extra human thinking between bad agents and good agents, even if not perfect. Softening some blows, for some time, by directing peoples attention is still good.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.