x

LESSWRONG
LW

Scalable Oversight — LessWrong

Scalable Oversight

This page is a stub.

Posts tagged Scalable Oversight

6

37Scaling Laws for Scalable Oversight

Subhash Kantamneni, Josh Engels, David Baek, Max Tegmark

7mo

1

2

115Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight

2y

10

2

92Learning the prior

paulfchristiano

5y

28

2

86Scalable oversight as a quantitative rather than qualitative problem

1y

11

2

46Gradient routing is better than pretraining filtering

3mo

3

2

31Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir, JacksonKaunismaa

1y

0

2

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

1y

0

2

18Rational Animations' video about scalable oversight and sandwiching

5mo

0

1

197[Research Note] Optimizing The Final Output Can Obfuscate CoT

lukemarks, jacob_drori, cloud, TurnTrout

4mo

22

1

169Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

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

1y

14

1

88Prover-Estimator Debate: A New Scalable Oversight Protocol

Jonah Brown-Cohen, Geoffrey Irving

6mo

18

1

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

1

27NYU Code Debates Update/Postmortem

2y

4

1

27Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain, Sophie Bridgers

1y

4

1

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

10mo

1

Load More (15/21)

Add Posts