LESSWRONG
LW

Scalable Oversight

This page is a stub.

Posts tagged Scalable Oversight

34Scaling Laws for Scalable Oversight

Subhash Kantamneni, Josh Engels, David Baek, Max Tegmark

2mo

0

113Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight

1y

10

92Learning the prior

paulfchristiano

5y

28

86Scalable oversight as a quantitative rather than qualitative problem

1y

11

31Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir, JacksonKaunismaa

1y

0

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

11mo

0

17Rational Animations' video about scalable oversight and sandwiching

6d

0

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

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

7mo

12

88Prover-Estimator Debate: A New Scalable Oversight Protocol

Jonah Brown-Cohen, Geoffrey Irving

25d

18

49On scalable oversight with weak LLMs judging strong LLMs

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

1y

18

27NYU Code Debates Update/Postmortem

1y

4

27Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain, Sophie Bridgers

7mo

4

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

5mo

1

7Evaluating Oversight Robustness with Incentivized Reward Hacking

Yoav, Juan V, julianjm, McKennaFitzgerald

3mo

2

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

Abhimanyu Pallavi Sudhir

10mo

2

Load More (15/17)

Add Posts