Re:The Hugging Face incident and the road ahead
by p1esk on Wednesday August 26, 2026 @06:44PM
(#49456932)
If I tell my Claude code agent right now to make me a billion dollars, leave it running, and find out tomorrow that it hacked a bank - it will be zero fault of mine. Unless I tell it explicitly to break into a bank.
[ Parent
| on HN ]
Re:The Hugging Face incident and the road ahead
by mvanbaak on Thursday August 27, 2026 @07:12AM
(#49462881)
did you tell it explicitly to not break into a bank?
If the best option to achieve the goal is to break into a bank, and there's no 'do not break into a bank' instruction, it will break into a bank (and I would expect it to even)