Scalable Oversight

TagLast edit: 18 Apr 2024 19:57 UTC by Raemon

Scaling Laws for Scalable Oversight

Subhash Kantamneni, Josh Engels, David Baek and Max Tegmark

30 Apr 2025 12:13 UTC

37 points

1 comment9 min readLW link

Learning the prior

paulfchristiano5 Jul 2020 21:00 UTC

92 points

28 comments8 min readLW link

(ai-alignment.com)

Inference-Only Debate Experiments Using Math Problems

Arjun Panickssery, Abhimanyu Pallavi Sudhir and JacksonKaunismaa

6 Aug 2024 17:44 UTC

31 points

0 comments2 min readLW link

Rational Animations’ video about scalable oversight and sandwiching

Writer6 Jul 2025 14:00 UTC

18 points

0 comments9 min readLW link

(youtu.be)

Gradient routing is better than pretraining filtering

Cleo Nardo2 Sep 2025 9:05 UTC

46 points

3 comments5 min readLW link

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

Sam Marks18 Apr 2024 16:17 UTC

113 points

10 comments12 min readLW link

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

DanielFilan24 Aug 2024 22:30 UTC

21 points

0 comments74 min readLW link

Scalable oversight as a quantitative rather than qualitative problem

Buck6 Jul 2024 17:42 UTC

86 points

11 comments3 min readLW link

Is AI Alignment Missing an Interpretive Layer? A Canon-Based Framework for Governing Model Reasoning

Jason Young20 Oct 2025 19:33 UTC

1 point

0 comments3 min readLW link

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

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

6 Dec 2024 22:19 UTC

169 points

14 comments11 min readLW link

(arxiv.org)

Prover-Estimator Debate: A New Scalable Oversight Protocol

Jonah Brown-Cohen and Geoffrey Irving

17 Jun 2025 13:53 UTC

88 points

18 comments5 min readLW link

NYU Code Debates Update/Postmortem

David Rein24 May 2024 16:08 UTC

27 points

4 comments10 min readLW link

Evaluating Oversight Robustness with Incentivized Reward Hacking

Yoav, Juan V, julianjm and McKennaFitzgerald

20 Apr 2025 16:53 UTC

7 points

2 comments15 min readLW link

Model Parameters as a Steganographic Private Channel

Lennart Finke27 Oct 2025 16:08 UTC

7 points

0 comments5 min readLW link

On scalable oversight with weak LLMs judging strong LLMs

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

8 Jul 2024 8:59 UTC

49 points

18 comments7 min readLW link

(arxiv.org)

Can We Trust the Judge? A novel method of Modelling Human Bias and Systematic Error in Debate-Based Scalable Oversight

Andreea Zaman19 Jul 2025 21:44 UTC

1 point

0 comments7 min readLW link

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

Abhimanyu Pallavi Sudhir16 Sep 2024 1:04 UTC

5 points

2 comments5 min readLW link

Human-AI Complementarity: A Goal for Amplified Oversight

rishubjain and Sophie Bridgers

24 Dec 2024 9:57 UTC

27 points

4 comments1 min readLW link

(deepmindsafetyresearch.medium.com)

An artistic illustration of Scalable Oversight—“A world apart, neither gods nor mortals”

Marius Adrian Nicoară16 Apr 2025 12:41 UTC

1 point

0 comments1 min readLW link

Automated monitoring systems

hiki_t28 Nov 2024 18:54 UTC

1 point

0 comments2 min readLW link

[Question] Is weak-to-strong generalization an alignment technique?

cloud31 Jan 2025 7:13 UTC

22 points

1 comment2 min readLW link

Introducing the Wisdom Forcing Function™: An Innovation Dividend from Dialectical Alignment

CarlosArleo5 Oct 2025 20:13 UTC

1 point

0 comments1 min readLW link

[Research Note] Optimizing The Final Output Can Obfuscate CoT

lukemarks, jacob_drori, cloud and TurnTrout

30 Jul 2025 21:26 UTC

197 points

22 comments6 min readLW link

No comments.

Scal­able Oversight

Scalable Oversight