✳flâneur — a map of the web's best reading

My AGI safety research—2024 review, ’25 plans — AI Alignment Forum

alignmentforum.org · 3,572 words · saved by 1 readers

“Our greatest fear should not be of failure, but of succeeding at something that doesn't really matter.” –attributed to DL Moody (copied almost word-for-word from Neuroscience of human social instincts: a sketch) My primary neuroscience research goal for the past couple years has been to solve a certain problem, a problem which has had me stumped since the very beginning of when I became interested in neuroscience at all (as a lens into Artificial General Intelligence safety) back in 2019. What is this grand problem? As described in Intro to Brain-Like-AGI Safety, I believe the following: It was a banner year! Basically, for years, I’ve had a vague idea about how human social instincts might work, involving what I call “transient empathetic simulations”. But I didn’t know how to pin it down in more detail than that. One subproblem was: I didn’t have even one example of a specific social instinct based on this putative mechanism—i.e., a hypothesis where a specific innate reaction would

x My AGI safety research—2024 review, ’25 plans — AI Alignment Forum Research Agendas AI Frontpage 45 My AGI safety research—2024 review, ’25 plans by Steven Byrnes 31st Dec 2024 10 min read 5 45 Previous: My AGI safety research—2022 review, ’23 plans . (I guess I skipped it last year.) “Our greatest fear should not be of failure, but of succeeding at something that doesn't really matter.” – attributed to DL Moody Tl;dr Section 1 goes through my main research project, “reverse-engineering human social instincts”: what does that even mean, what’s the path-to-impact, what progress did I make in

Explore this link on the map →

related reading