Yep, it's not as far fetched as it would've been a year ago. A scenario where yo... | Hacker News

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

		helloplanets 6 months ago \| parent \| context \| favorite \| on: 'Positive review only': Researchers hide AI prompt... Yep, it's not as far fetched as it would've been a year ago. A scenario where you're running an agent in 'yolo mode', it opening up some poisonous readme / docs / paper, and then executing the wrong shell command.

nerdsniper 6 months ago [–]

Could be done responsibly if you run it in a VM to sandbox it with incremental backup so you can roll-back if something is deleted?

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