Sam Bowman

Karma: 1,909

https://cims.nyu.edu/~sbowman/

Building and evaluating alignment auditing agents

Sam Marks, trentbrick, RowanWang, Sam Bowman, Euan Ong, Johannes Treutlein and evhub

24 Jul 2025 19:22 UTC

47 points

1 comment5 min readLW link

Putting up Bumpers

Sam Bowman23 Apr 2025 16:05 UTC

55 points

14 comments2 min readLW link

Automated Researchers Can Subtly Sandbag

gasteigerjo, Akbir Khan, Sam Bowman, Vlad Mikulik, Ethan Perez and Fabien Roger

26 Mar 2025 19:13 UTC

44 points

0 comments4 min readLW link

(alignment.anthropic.com)

Auditing language models for hidden objectives

Sam Marks, Johannes Treutlein, dmz, Sam Bowman, Hoagy, Carson Denison, Kei Nishimura-Gasparian, 7vik, Akbir Khan, Austin Meek, Euan Ong, Christopher Olah, Fabien Roger, jeanne_, Meg, Drake Thomas, Adam Jermyn, Monte M and evhub

13 Mar 2025 19:18 UTC

142 points

15 comments13 min readLW link

Alignment Faking in Large Language Models

ryan_greenblatt, evhub, Carson Denison, Benjamin Wright, Fabien Roger, Monte M, Sam Marks, Johannes Treutlein, Sam Bowman and Buck

18 Dec 2024 17:19 UTC

490 points

75 comments10 min readLW link

Sabotage Evaluations for Frontier Models

David Duvenaud, Joe Benton, Sam Bowman, evhub, mishajw, Eric Christiansen, HoldenKarnofsky, Ethan Perez and Buck

18 Oct 2024 22:33 UTC

95 points

56 comments6 min readLW link

(assets.anthropic.com)

The Checklist: What Succeeding at AI Safety Will Involve

Sam Bowman3 Sep 2024 18:18 UTC

151 points

50 comments22 min readLW link

(sleepinyourhat.github.io)

Simple probes can catch sleeper agents

Monte M, Carson Denison, Zac Hatfield-Dodds, David Duvenaud, Sam Bowman, Ethan Perez and evhub

23 Apr 2024 21:10 UTC

133 points

21 comments1 min readLW link

(www.anthropic.com)

LLM Evaluators Recognize and Favor Their Own Generations

Arjun Panickssery, Sam Bowman and Shi Feng

17 Apr 2024 21:09 UTC

49 points

1 comment3 min readLW link

(tiny.cc)

Debating with More Persuasive LLMs Leads to More Truthful Answers

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

7 Feb 2024 21:28 UTC

89 points

14 comments9 min readLW link

(arxiv.org)

Measuring and Improving the Faithfulness of Model-Generated Reasoning

Ansh Radhakrishnan, tamera, karinanguyen, Sam Bowman and Ethan Perez

18 Jul 2023 16:36 UTC

111 points

15 comments6 min readLW link 1 review

Pretraining Language Models with Human Preferences

Tomek Korbak, Sam Bowman and Ethan Perez

21 Feb 2023 17:57 UTC

135 points

20 comments11 min readLW link 2 reviews

Inverse Scaling Prize: Second Round Winners

Ian McKenzie, Sam Bowman and Ethan Perez

24 Jan 2023 20:12 UTC

58 points

17 comments15 min readLW link

AI Safety and Neighboring Communities: A Quick-Start Guide, as of Summer 2022

Sam Bowman1 Sep 2022 19:15 UTC

76 points

2 comments7 min readLW link

Survey of NLP Researchers: NLP is contributing to AGI progress; major catastrophe plausible

Sam Bowman31 Aug 2022 1:39 UTC

91 points

6 comments2 min readLW link

Artificial Sandwiching: When can we test scalable alignment protocols without humans?

Sam Bowman13 Jul 2022 21:14 UTC

42 points

6 comments5 min readLW link

Announcing the Inverse Scaling Prize ($250k Prize Pool)

Ethan Perez, Ian McKenzie and Sam Bowman

27 Jun 2022 15:58 UTC

171 points

14 comments7 min readLW link

Jobs: Help scale up LM alignment research at NYU

Sam Bowman9 May 2022 14:12 UTC

60 points

1 comment1 min readLW link

A Small Negative Result on Debate

Sam Bowman12 Apr 2022 18:19 UTC

42 points

11 comments1 min readLW link

NLP Position Paper: When Combatting Hype, Proceed with Caution

Sam Bowman15 Oct 2021 20:57 UTC

46 points

14 comments1 min readLW link