Regarding thinking about what to do in the endgame:
Having a bunch of practice at thinking about AI alignment in principle, which might be really useful for answering difficult-to-empirically-resolve questions about the AIs being trained.
Being well-prepared to use AI cognitive labor to do something useful, by knowing a lot about some research topic that we end up wanting to put lots of AI labor into. Maybe you could call this “preparing to be a research lead for a research group made up of AIs”. Or “preparing to be good at consuming AI research labor”.
That nicely put into words how I’m partially planning my “accelerating alignment with language models” agenda. I hope to come up with something that allows all alignment researchers to do the above with minimal friction and set up, and obvious benefit.
Regarding thinking about what to do in the endgame:
That nicely put into words how I’m partially planning my “accelerating alignment with language models” agenda. I hope to come up with something that allows all alignment researchers to do the above with minimal friction and set up, and obvious benefit.