Scalable Oversight

Applied to Gradient Routing: Masking Gradients to Localize Computation in Neural Networks by Alex Turner 12d ago

Applied to Automated monitoring systems by Hikaru Tsujimura 20d ago

Applied to Ways to think about alignment by Abhimanyu Pallavi Sudhir 2mo ago

Applied to Reinforcement Learning from Information Bazaar Feedback, and other uses of information markets by Abhimanyu Pallavi Sudhir 3mo ago

Applied to AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization by DanielFilan 4mo ago

Applied to Inference-Only Debate Experiments Using Math Problems by Arjun Panickssery 4mo ago

Applied to Scalable oversight as a quantitative rather than qualitative problem by Ruben Bloom 5mo ago

Applied to On scalable oversight with weak LLMs judging strong LLMs by Zachary Kenton 5mo ago

Applied to NYU Code Debates Update/Postmortem by David Rein 7mo ago

Applied to Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight by Raymond Arnold 8mo ago

Created by Raymond Arnold at 8mo