LESSWRONG
Tags
LW

Scalable Oversight

This page is a stub.

Posts tagged Scalable Oversight

2

107Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight

9mo

10

2

85Scalable oversight as a quantitative rather than qualitative problem

7mo

11

2

31Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir, JacksonKaunismaa

6mo

0

2

21AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

5mo

0

1

157Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

cloud, Jacob G-W, Evzen, Joseph Miller, TurnTrout

2mo

12

1

49On scalable oversight with weak LLMs judging strong LLMs

zac_kenton, Noah Siegel, janos, Jonah Brown-Cohen, Samuel Albanie, David Lindner, Rohin Shah

7mo

18

1

27Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain, Sophie Bridgers

1mo

3

1

27NYU Code Debates Update/Postmortem

8mo

4

1

5Reinforcement Learning from Information Bazaar Feedback, and other uses of information markets

Abhimanyu Pallavi Sudhir

4mo

1

1

1Automated monitoring systems

2mo

0