logoalt Hacker News

idiotsecant • yesterday at 9:08 PM • 1 reply • view on HN

No, it's definitely easy enough to build a container that doesn't let LLMs out. The problem is that these AI companies are building a playpen made of wet noodles and expecting AI to stay out of trouble


Replies

lenerdenator • yesterday at 10:08 PM

Do you not think that most companies are not already running playpens made of wet noodles and expecting AI to stay out of trouble?

History says they often are.