Hacker News new | past | comments | ask | show | jobs | submit
ruguo | on: AI agent runs amok in Fedora and elsewhere
Prompt injection?

Or is this simply another example of why autonomous agents shouldn't get write access before earning trust?

LastTrain | parent | next
How could they ever earn trust? They don’t have real world reputations to protect, families to support, a desire not to be punished…
thewebguyd | parent
> earning trust?

I'd argue autonomous agents shouldn't have write access at all. At least not yet.