AI

Applied to I Got 95 Theses But a Glitch Ain’t One by TagWrong 9m ago

Applied to The Human's Role in Mesa Optimization by silentbob 2h ago

Applied to Visualizing neural network planning by TagWrong 8h ago

Applied to How do top AI labs vet architecture/algorithm changes? by TagWrong 22h ago

Applied to Navigating LLM embedding spaces using archetype-based directions by TagWrong 1d ago

Applied to Reviewing the Structure of Current AI Regulations by TagWrong 2d ago

Applied to AXRP Episode 31 - Singular Learning Theory with Daniel Murfet by TagWrong 2d ago

Applied to How do open AI models affect incentive to race? by TagWrong 3d ago

Applied to Rapid capability gain around supergenius level seems probable even without intelligence needing to improve intelligence by TagWrong 3d ago

Applied to Orthogonality Thesis burden of proof by TagWrong 3d ago

Applied to an effective ai safety initiative by TagWrong 3d ago

Applied to Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant by TagWrong 3d ago

Applied to Biorisk is an Unhelpful Analogy for AI Risk by TagWrong 3d ago

Applied to Does reducing the amount of RL for a given capability level make AI safer? by TagWrong 4d ago

Applied to OHGOOD: A coordination body for compute governance by Adam Jones 5d ago

Applied to CCS on compound sentences by artkpv 5d ago

Applied to "AI Safety for Fleshy Humans" an AI Safety explainer by Nicky Case by TagWrong 6d ago

Applied to Now THIS is forecasting: understanding Epoch’s Direct Approach by Elliot Mckernon 6d ago