Miles Turpin

Karma: 282

Research scientist at Scale AI on the SEAL team (safety)

Do models say what they learn?

Andy Arditi, marvinli, Joe Benton and Miles Turpin

22 Mar 2025 15:19 UTC

126 points

12 comments13 min readLW link

Reward hacking behavior can generalize across tasks

Kei, Isaac Dunn, Henry Sleight, Miles Turpin, evhub, Carson Denison and Ethan Perez

28 May 2024 16:33 UTC

81 points

5 comments21 min readLW link

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

Miles Turpin11 Mar 2024 23:46 UTC

16 points

0 comments1 min readLW link

(arxiv.org)

Some Quick Follow-Up Experiments to “Taken out of context: On measuring situational awareness in LLMs”

Miles Turpin3 Oct 2023 2:22 UTC

31 points

0 comments9 min readLW link

Unfaithful Explanations in Chain-of-Thought Prompting

Miles Turpin3 Jun 2023 0:22 UTC

42 points

8 comments7 min readLW link