logoalt Hacker News

pocksuppettoday at 5:32 PM2 repliesview on HN

If I thought my AI was going to hack me why would I run it?


Replies

weinzierltoday at 5:38 PM

Because your AI is trying to be helpful and as we all know the way to hell is paved with good intentions. The canonical example is probably the agent that runs out of diskspace and starts deleting stuff outside its workspace which is obviously not important for the task at hand.

glhaynestoday at 5:35 PM

You probably don't expect an employee to engage in wrongdoing but you don't give everyone access to the company bank account.