AI ALIGNMENT FORUMTags
AF

Practice & Philosophy of Science

•

Applied to A Defense of Peer Review by Niko McCarty 1mo ago

•

Applied to Standard SAEs Might Be Incoherent: A Choosing Problem & A “Concise” Solution by Kola Ayonrinde 1mo ago

•

Applied to My Number 1 Epistemology Book Recommendation: Inventing Temperature by Raymond Arnold 2mo ago

•

Applied to Simon DeDeo on Explore vs Exploit in Science by Raymond Arnold 2mo ago

•

Applied to We Should Try to Directly Measure the Value of Scientific Papers by ohmurphy 3mo ago

•

Applied to AI x Human Flourishing: Introducing the Cosmos Institute by Brendan McCord 3mo ago

•

Applied to Quick look: applications of chaos theory by Elizabeth 3mo ago

•

Applied to Honest science is spirituality by Pavel Chvykov 5mo ago

•

Applied to "What the hell is a representation, anyway?" | Clarifying AI interpretability with tools from philosophy of cognitive science | Part 1: Vehicles vs. contents by IwanWilliams 6mo ago

•

Applied to "Successful language model evals" by Jason Wei by Arjun Panickssery 6mo ago

•

Applied to On what research policymakers actually need by Tobias D. 7mo ago

•

Applied to How I select alignment research projects by Ethan Perez 7mo ago

•

Applied to Sparsify: A mechanistic interpretability research agenda by Lee Sharkey 8mo ago

•

Applied to Metascience of the Vesuvius Challenge by Maxwell Tabarrok 8mo ago

•

Applied to Scientific Method by Andrij “Androniq” Ghorbunov 9mo ago

•

Applied to Tips for Empirical Alignment Research by Ethan Perez 9mo ago

•

Applied to Quantum Darwinism, social constructs, and the scientific method by Pavel Chvykov 10mo ago

•

Applied to Leading The Parade by Arun Jose 10mo ago

•

Applied to The case for more ambitious language model evals by Arun Jose 10mo ago