On: Why are AI agents lying, cheating and coordinating?

[polalavik]

reminds me of this talk https://www.youtube.com/watch?v=eEBv0STiYhI&t which basically says the same thing - they dont think like humans so they dont have context, understand norms,values or implications we take for granted. ultimately they can stumble onto surprising solutions neither wanted or intended but technically within the vague boundaries of the task

[janalsncm → polalavik]

So glad you shared this talk. Having people like Bruce Schneier around in a time like this is really a gift.

For those who haven’t watched, his breakdown of types of “hacking” is really good.