Humans missed 1 in 3 threats approving AI agent commands across 40k game runs
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Humans missed 1 in 3 threats approving AI agent commands across 40k game runs
Unofficial Hacker News client; not affiliated with Y Combinator.
xlii · · focus · HN ↗
Context-less self-approval is working well. The failure mode is usually false positives (i.e. safe commands being rejected), not the other way around, with root cause of requesting agent underspecifying context (e.g. not mentioning in the request that it's made on behalf of user etc.)
Thus, I'm running self-approval YOLO modes on state-of-the-art models for quite some time and it didn't bit me. It might, but hey, we're long gone from the age of predictable software development.