Conjecture (org)

Applied to Barriers to Mechanistic Interpretability for AGI Safety by Connor Leahy 1mo ago

Applied to Introducing EffiSciences’ AI Safety Unit  by Charbel-Raphael Segerie 3mo ago

Applied to Conjecture: A standing offer for public debates on AI by Andrea_Miotti 4mo ago

Applied to Critiques of prominent AI safety labs: Conjecture by Anonymous Omega 4mo ago

Applied to Conjecture internal survey: AGI timelines and probability of human extinction from advanced AI by Maris Sala 4mo ago

Applied to A technical note on bilinear layers for interpretability by Lee Sharkey 5mo ago

Applied to Shah (DeepMind) and Leahy (Conjecture) Discuss Alignment Cruxes by Olivia Jimenez 5mo ago

Applied to A response to Conjecture's CoEm proposal by Kristian Freed 5mo ago

Applied to Japan AI Alignment Conference Postmortem by Chris Scammell 5mo ago

Applied to A couple of questions about Conjecture's Cognitive Emulation proposal by Igor Ivanov 6mo ago

Applied to Japan AI Alignment Conference by Andrea_Miotti 7mo ago

Applied to Questions about Conjecure's CoEm proposal by Akash 7mo ago

Applied to Cognitive Emulation: A Naive AI Safety Proposal by Connor Leahy 7mo ago

Applied to Christiano (ARC) and GA (Conjecture) Discuss Alignment Cruxes by Andrea_Miotti 7mo ago

Applied to Retrospective on the 2022 Conjecture AI Discussions by Andrea_Miotti 7mo ago

Applied to Basic facts about language models during training by Beren Millidge 7mo ago

Applied to AGI in sight: our look at the game board by Andrea_Miotti 7mo ago