LESSWRONG
Wikitags
LW

Scalable Oversight

This page is a stub.

Posts tagged Scalable Oversight

2

110Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight

1y

10

2

85Scalable oversight as a quantitative rather than qualitative problem

9mo

11

2

31Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir, JacksonKaunismaa

8mo

0

2

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

7mo

0

1

165Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

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

4mo

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

9mo

18

1

27Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain, Sophie Bridgers

3mo

4

1

27NYU Code Debates Update/Postmortem

10mo

4

1

22Is weak-to-strong generalization an alignment technique?

2mo

1

1

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

Abhimanyu Pallavi Sudhir

6mo

1

1

1Automated monitoring systems

4mo

0