Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Which is weird since this is not a criticism on AI. I really want to know how I can use things like Claude Work without the risk of it going rogue! Giving it access to lots of systems is potentially very valuable, but also so dangerous that I dare not to.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: