Scalable Oversight

Applied to Ways to think about alignment by Abhimanyu Pallavi Sudhir 22d ago

Applied to Reinforcement Learning from Information Bazaar Feedback, and other uses of information markets by Abhimanyu Pallavi Sudhir 2mo ago

Applied to AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization by DanielFilan 3mo ago

Applied to Inference-Only Debate Experiments Using Math Problems by Arjun Panickssery 3mo ago

Applied to Scalable oversight as a quantitative rather than qualitative problem by Ruben Bloom 4mo ago

Applied to On scalable oversight with weak LLMs judging strong LLMs by Zachary Kenton 4mo ago

Applied to NYU Code Debates Update/Postmortem by David Rein 6mo ago

Applied to Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight by Raymond Arnold 7mo ago

Created by Raymond Arnold at 7mo