Jonah Brown-Cohen

Karma: 227

Debate Training Reduces Reward Hacking in RLAIF

zac_kenton and Jonah Brown-Cohen

19 Aug 2026 12:17 UTC

61 points

6 comments6 min readLW link

(gdmalignment.substack.com)

Prover-Estimator Debate: A New Scalable Oversight Protocol

Jonah Brown-Cohen and Geoffrey Irving

17 Jun 2025 13:53 UTC

89 points

19 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)

Debate, Oracles, and Obfuscated Arguments

Jonah Brown-Cohen and Geoffrey Irving

20 Jun 2024 23:14 UTC

45 points

4 comments21 min readLW link