AI alignment

Applied to A discussion with ChatGPT on value-based models vs. large language models, etc.. by Miguel at 3d

Applied to An audio version of the alignment problem from a deep learning perspective by Richard Ngo Et Al by Miguel at 4d

Applied to I asked ChatGPT about pattern recognition, alignment and fairness constraints. by Miguel at 5d

Applied to Focus on the places where you feel shocked everyone's dropping the ball by Owen Murphy at 6d

Applied to Alexander and Yudkowsky on AGI goals by Owen Murphy at 7d

Applied to [Linkpost] Human-narrated audio version of "Is Power-Seeking AI an Existential Risk?" by Owen Murphy at 7d

Applied to Eli Lifland on Navigating the AI Alignment Landscape by Ozzie Gooen at 7d

Applied to On value in humans, other animals, and AI by Michele Campolo at 7d

Applied to What Are The Biggest Threats To Humanity? (A Happier World video) by Jeroen Willems at 7d

Applied to Alignment is mostly about making cognition aimable at all by Lorenzo Buonanno at 8d

Applied to Compendium of problems with RLHF by Amber Dawn at 8d

Applied to 11 heuristics for choosing (alignment) research projects by Owen Murphy at 12d

Applied to Large Language Models as Fiduciaries to Humans by johnjnay at 14d

Applied to Any Philosophy PhD recommendations for students interested in Alignment Efforts? by Owen Murphy at 21d

Applied to Emerging Paradigms: The Case of Artificial Intelligence Safety by Eleni_A at 21d

Applied to Collin Burns on Alignment Research And Discovering Latent Knowledge Without Supervision by Amber Dawn at 21d

Applied to Jan Kirchner on AI Alignment by birtes at 21d

Applied to Preparing for AI-assisted alignment research: we need data! by CBiddulph at 22d