Thread

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

226 points · 178 comments · Wirbelwind

continuational · 1786022679 · 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. RankingMember · 1786037347 · focus · HN ↗
  Yep, file it in the same folder as "Terms and Conditions" notices.

Unofficial Hacker News client; not affiliated with Y Combinator.