AI ALIGNMENT FORUMTags
AF

AI-assisted/AI automated Alignment

•

Applied to AISC project: How promising is automating alignment research? (literature review) by Bogdan Ionut Cirstea 1h ago

•

Applied to 2. AIs as Economic Agents by Roger Dearnaley 6d ago

•

Applied to 1. A Sense of Fairness by Roger Dearnaley 8d ago

•

Applied to Shouldn't we 'Just' Superimitate Low-Res Uploads? by lukemarks 25d ago

•

Applied to Could We Automate AI Alignment Research? by Stephen McAleese 4mo ago

•

Applied to Have you ever considered taking the 'Turing Test' yourself? by Super AGI 4mo ago

•

Applied to Robustness of Model-Graded Evaluations and Automated Interpretability by Simon Lermen 5mo ago

•

Applied to How I Learned To Stop Worrying And Love The Shoggoth by Peter Merel 5mo ago

•

Applied to OpenAI Launches Superalignment Taskforce by Christopher King 5mo ago

•

Applied to [Linkpost] Introducing Superalignment by Christopher King 5mo ago

•

Applied to Philosophical Cyborg (Part 2)...or, The Good Successor by ukc10014 5mo ago

•

Applied to What will GPT-2030 look like? by Charbel-Raphael Segerie 6mo ago

•

Applied to A potentially high impact differential technological development area by Noosphere89 6mo ago

•

Applied to An LLM-based “exemplary actor” by Roman Leventov 6mo ago

•

Applied to Requirements for a STEM-capable AGI Value Learner (my Case for Less Doom) by Roger Dearnaley 6mo ago

•

Applied to Proposed Alignment Technique: OSNR (Output Sanitization via Noising and Reconstruction) for Safer Usage of Potentially Misaligned AGI by Alana 6mo ago

•

Applied to Misaligned AGI Death Match by Ruben Bloom 6mo ago