Research Agendas

Applied to Agency overhang as a proxy for Sharp left turn by Eris 9d ago

Applied to Seeking Collaborators by Steven Byrnes 14d ago

Applied to Self-prediction acts as an emergent regularizer by Cameron Berg 23d ago

Applied to NAO Updates, Fall 2024 by ProgramCrafter 1mo ago

Applied to Towards the Operationalization of Philosophy & Wisdom by Thane Ruthenis 1mo ago

Applied to [Linkpost] Interpretable Analysis of Features Found in Open-source Sparse Autoencoder (partial replication) by Fernando Avalos 2mo ago

Applied to Why Academia is Mostly Not Truth-Seeking by Zero Contradictions 4mo ago

Applied to What and Why: Developmental Interpretability of Reinforcement Learning by Ruby 4mo ago

Applied to Labor Participation is a High-Priority AI Alignment Risk by alex 5mo ago

Applied to What should I do? (long term plan about starting an AI lab) by not_a_cat 5mo ago

Applied to What should AI safety be trying to achieve? by EuanMcLean 6mo ago

Applied to Announcing Human-aligned AI Summer School by Jan_Kulveit 6mo ago

Applied to EIS XIII: Reflections on Anthropic’s SAE Research Circa May 2024 by scasper 6mo ago

Applied to The Prop-room and Stage Cognitive Architecture by Robert Kralisch 7mo ago

Applied to Speedrun ruiner research idea by lukehmiles 7mo ago

Applied to Constructability: Plainly-coded AGIs may be feasible in the near future by Charbel-Raphaël 7mo ago

Applied to Sparsify: A mechanistic interpretability research agenda by Marius Hobbhahn 7mo ago

Applied to Gradient Descent on the Human Brain by Jozdien 8mo ago