x

AI ALIGNMENT FORUM
AF

Scalable Oversight — AI Alignment Forum

Scalable Oversight

This page is a stub.

Posts tagged Scalable Oversight

1

59Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight

2y

7

0

43Learning the prior

paulfchristiano

5y

23

1

43Scalable oversight as a quantitative rather than qualitative problem

1y

8

1

15Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir, JacksonKaunismaa

1y

0

2

13AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization

1y

0

1

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

lukemarks, jacob_drori, cloud, TurnTrout

4mo

3

2

64Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

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

1y

4

1

42Prover-Estimator Debate: A New Scalable Oversight Protocol

Jonah Brown-Cohen, Geoffrey Irving

6mo

17

1

22On scalable oversight with weak LLMs judging strong LLMs

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

1y

18

0

17Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain, Sophie Bridgers

1y

3

1

14Is weak-to-strong generalization an alignment technique?

10mo

1

Add Posts