Simon Mendelsohn
51
4
Simon Mendelsohn has not written any posts yet.
Simon Mendelsohn has not written any posts yet.
This is hilarious and beautiful and exactly what I expect from LessWrong. Also, hello fellow Simon.
I feel like we already can point powerful cognition at certain things pretty well (e.g. chess), and the problem is figuring out how to point AIs to more useful things (e.g. honestly answering hard questions well). So I don’t know if I’m nit-picky, but I think that the problem is not pointing powerful cognition at anything at all, but rather pointing powerful cognition at whatever we want.
Good paper! Thank you for sharing. I have a few nit-picky suggestions with wording and grammar. I will put them here rather than email directly because some of them are subjective. This way others can feel free to chime in if they feel inclined to nit-pick my nit-picks :)
"artificial general intelligence (AGI) may surpass" -> "artificial general intelligence (AGI) seems likely to surpass" (I feel like "may" is a somewhat weak word in this context, but I don't feel strongly here.)
"undesirable (in other words, misaligned)" -> "undesirable (i.e., misaligned)" (This is precisely the situation when "i.e.," applies, and I think it's cleaner.)
"trained in similar ways as today's" -> "trained in similar ways... (read more)
There are frequently such typos in your posts. I'm curious if this is an intentional choice to differentiate yourself from AI writing or if just don't bother with a spell-checker?
(p.s. thank you for your hard work on your great blog posts!)