AI Oversight

Applied to AI Safety Oversights by Davey Morse 2mo ago

Applied to Activation Magnitudes Matter On Their Own: Insights from Language Model Distributional Analysis by Matt Levinson 3mo ago

Applied to Human-AI Complementarity: A Goal for Amplified Oversight by Rishub Jain 3mo ago

Applied to W2SG: Introduction by Maria Kapros 1y ago

Applied to The weak-to-strong generalization (WTSG) paper in 60 seconds by Alana 1y ago

Applied to Measuring and Improving the Faithfulness of Model-Generated Reasoning by Henning Bartsch 1y ago

Applied to Is there any existing term summarizing non-scalable oversight methods in outer alignment? by Allen Shen 2y ago

Applied to Trying to measure AI deception capabilities using temporary simulation fine-tuning by Alain Le Noac'h 2y ago

Applied to Oversight Misses 100% of Thoughts The AI Does Not Think by Thomas Kwa 2y ago

Applied to "Corrigibility at some small length" by dath ilan by Christopher King 2y ago

Applied to Quick thoughts on "scalable oversight" / "super-human feedback" research by RobertM 2y ago

Applied to Doing oversight from the very start of training seems hard by RobertM 3y ago

Created by RobertM at 3y