John Hughes

Karma: 438

Former MATS scholar working on scalable oversight and adversarial robustness.

Alignment Faking Revisited: Improved Classifiers and Open Source Extensions

John Hughes, abhayesian, Akbir Khan and Fabien Roger

Apr 8, 2025, 5:32 PM

146 points

20 comments12 min readLW link

Tips and Code for Empirical Research Workflows

John Hughes and Ethan Perez

Jan 20, 2025, 10:31 PM

94 points

14 comments20 min readLW link

Tips On Empirical Research Slides

James Chua, John Hughes, Ethan Perez and Owain_Evans

Jan 8, 2025, 5:06 AM

90 points

4 comments6 min readLW link

Best-of-N Jailbreaking

John Hughes, saraprice, Aengus Lynch, Rylan Schaeffer, Fazl, Henry Sleight, Ethan Perez and mrinank_sharma

Dec 14, 2024, 4:58 AM

78 points

5 comments2 min readLW link

(arxiv.org)

Debating with More Persuasive LLMs Leads to More Truthful Answers

Akbir Khan, John Hughes, Dan Valentine, Sam Bowman and Ethan Perez

Feb 7, 2024, 9:28 PM

89 points

14 comments9 min readLW link

(arxiv.org)