Thread

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

208 points · 169 comments · Wirbelwind

deeviant · 1786039035 · focus · HN ↗
Yeah if you are trying to manually validate a firehouse of agent commands you are already losing before you started...
You sandbox, you have good checkpoints, and good agents, that's it. If you are manually reviewing commands you are wasting your time.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.