US presidents rate AI alignment agendas
youtube.com · 148 words · saved by 3 readers
0:00 Intro1:21 Superposition3:44 Circuit interp6:30 Agent foundations (MIRI)12:19 CoEms (Conjecture)14:40 Infrabayesianism15:19 Shard theory19:25 Eliciting l...
0:00 Intro 1:21 Superposition 3:44 Circuit interp 6:30 Agent foundations (MIRI) 12:19 CoEms (Conjecture) 14:40 Infrabayesianism 15:19 Shard theory 19:25 Eliciting latent knowledge elevenlabs.io generated the voices. I wrote the script, with some help/edits from David Udell, Rio Popper, Noemi Chulo, and Ulisse Mini. Eliezer's time article [Pausing AI Developments Isn't Enough. We Need to Shut it All Down] https://time.com/6266923/ai-eliezer-y... Toy Models of Superposition: https://arxiv.org/abs/2209.10652 A Mathematical Framework for Transformer Circuits:…
saved by
related reading
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Where I agree and disagree with Eliezer — LessWronglesswrong.com
- AGI safety career advice — EA Forumforum.effectivealtruism.org
- The Best of LessWrong — LessWronglesswrong.com
- AI 2040: Plan Aai-2040.com
- A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
- Critical review of Christiano's disagreements with Yudkowsky — LessWronglesswrong.com
- The hot mess theory of AI misalignment: More intelligent agents behave less coherently | Jascha’s blogsohl-dickstein.github.io
- The Iliad Intensive Course Materials — LessWronglesswrong.com
- Shallow review of technical AI safety, 2024 — LessWronglesswrong.com