AI ALIGNMENT FORUM
AF

605

John Hughes

Ω141210

Former MATS scholar working on scalable oversight and adversarial robustness.

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No wikitag contributions to display.

Tips and Code for Empirical Research Workflows

John Hughes9mo20

Thanks Neel! I'm glad you found it helpful. If you or your scholars recommend any other tools not mentioned in the post, I'd be interested to hear more.

74Why Do Some Language Models Fake Alignment While Others Don't?

3mo

2

70Alignment Faking Revisited: Improved Classifiers and Open Source Extensions

6mo

6

40Tips and Code for Empirical Research Workflows

9mo

2

31Best-of-N Jailbreaking

10mo

1

47Debating with More Persuasive LLMs Leads to More Truthful Answers

2y

7