AI alignment

Applied to College technical AI safety hackathon retrospective - Georgia Tech 3d ago

Applied to Incentive design and capability elicitation 4d ago

Applied to Infinite Rewards, Finite Safety: New Models for AI Motivation Without Infinite Goals 5d ago

Applied to The King and the Golem - The Animation 9d ago

Applied to AI safety tax dynamics 12d ago

Applied to Option control 13d ago

Applied to Can we train AI so that future philanthropy is more effective? 13d ago

Applied to The Compendium, A full argument about extinction risk from AGI 17d ago

Applied to Motivation control 18d ago

Applied to AI & wisdom 3: AI effects on amortised optimisation 19d ago

Applied to How might we solve the alignment problem? (Part 1: Intro, summary, ontology) 19d ago

Applied to Miles Brundage resigned from OpenAI, and his AGI readiness team was disbanded 24d ago

Applied to A Rocket–Interpretability Analogy 1mo ago

Applied to AI data gaps could lead to ongoing Animal Suffering 1mo ago

Applied to Geoffrey Hinton on the Past, Present, and Future of AI 1mo ago

Applied to 5 ways to improve CoT faithfulness 1mo ago

Applied to Risk Alignment in Agentic AI Systems 2mo ago

Applied to Not Just For Therapy Chatbots: The Case For Compassion In AI Moral Alignment Research 2mo ago