Conjecture (org)

Applied to Conjecture internal survey: AGI timelines and probability of human extinction from advanced AI by Maris Sala 6 days ago

Applied to A technical note on bilinear layers for interpretability by Lee Sharkey 23 days ago

Applied to Shah (DeepMind) and Leahy (Conjecture) Discuss Alignment Cruxes by Olivia Jimenez 1mo ago

Applied to A response to Conjecture's CoEm proposal by Kristian Freed 1mo ago

Applied to Japan AI Alignment Conference Postmortem by Chris Scammell 1mo ago

Applied to A couple of questions about Conjecture's Cognitive Emulation proposal by Igor Ivanov 2mo ago

Applied to Japan AI Alignment Conference by Andrea_Miotti 3mo ago

Applied to Questions about Conjecure's CoEm proposal by Akash 3mo ago

Applied to Cognitive Emulation: A Naive AI Safety Proposal by Connor Leahy 3mo ago

Applied to Christiano (ARC) and GA (Conjecture) Discuss Alignment Cruxes by Andrea_Miotti 3mo ago

Applied to Retrospective on the 2022 Conjecture AI Discussions by Andrea_Miotti 3mo ago

Applied to Basic facts about language models during training by beren 3mo ago

Applied to AGI in sight: our look at the game board by Andrea_Miotti 3mo ago

Applied to Human decision processes are not well factored by remember 3mo ago

Applied to Don't accelerate problems you're trying to solve by Andrea_Miotti 3mo ago

Applied to Why almost every RL agent does learned optimization by Andrea_Miotti 4mo ago

Applied to Empathy as a natural consequence of learnt reward models by Andrea_Miotti 4mo ago