[I’m doing a bunch of low-effort reviews of posts I read a while ago and think are important. Unfortunately, I don’t have time to re-read them or say very nuanced things about them.]
There’s been a variety of work over the last few years focused on examining the arguments for focusing on AI alignment. I think this is one of the better and more readable ones. It’s also quite long and not-really-on-the-Forum. Not sure what to do with that. The last post has a bunch of comment threads, which might be a good way of demonstrating EA reasoning.
[I’m doing a bunch of low-effort reviews of posts I read a while ago and think are important. Unfortunately, I don’t have time to re-read them or say very nuanced things about them.]
There’s been a variety of work over the last few years focused on examining the arguments for focusing on AI alignment. I think this is one of the better and more readable ones. It’s also quite long and not-really-on-the-Forum. Not sure what to do with that. The last post has a bunch of comment threads, which might be a good way of demonstrating EA reasoning.