Yeah these effects seem hugely foreseeable (and/or are currently happening already) but tend to not be the type of thing "AI risk" people are talking about.
Exactly! I am positive there will be a ton of negative impact, like with most (all?) of tech. And it might be worse than anything we’ve seen (although beating the Snapchat algo might prove tricky). But that’s NOT what Tegmark and Hofstadter are talking about… their concern is existential and somewhat philosophical in the case of Hofstadter, as if GPT-4 questioned his very nature. To me, that doesn’t make sense.
