Dylan Xu

Karma: 292

How to reduce capability degradation from off-model SFT

Dylan Xu, SebastianP and Alek Westover

8 Jun 2026 16:24 UTC

21 points

0 comments3 min readLW link

Advice for making robust-to-training model organisms

SebastianP, Alek Westover, Vivek Hebbar, Julian Stastny and Dylan Xu

28 May 2026 17:26 UTC

37 points

8 comments12 min readLW link

(blog.redwoodresearch.org)

Why does off-model SFT degrade capabilities?

SebastianP, Dylan Xu, Alek Westover, Julian Stastny and Vivek Hebbar

21 May 2026 0:35 UTC

42 points

9 comments6 min readLW link

Sleeper Agent Backdoor Results Are Messy

SebastianP, Alek Westover, Dylan Xu, Vivek Hebbar and Julian Stastny

28 Apr 2026 1:55 UTC

81 points

4 comments7 min readLW link

An Empirical Study of Methods for SFTing Opaque Reasoning Models

SebastianP, Alek Westover, Vivek Hebbar, Dylan Xu and Julian Stastny

24 Apr 2026 17:26 UTC

17 points

0 comments6 min readLW link

How do LLMs generalize when we do training that is intuitively compatible with two off-distribution behaviors?

Dylan Xu, Alek Westover, Vivek Hebbar, SebastianP, frisby and Julian Stastny

20 Apr 2026 16:58 UTC

62 points

5 comments20 min readLW link

Model organisms researchers should check whether high LRs defeat their model organisms

Dylan Xu, SebastianP, Alek Westover, Vivek Hebbar and Julian Stastny

10 Apr 2026 0:07 UTC

40 points

0 comments5 min readLW link

dx26′s Shortform

Dylan Xu16 Feb 2025 21:31 UTC

2 points

3 comments1 min readLW link

Measuring Coherence and Goal-Directedness in RL Policies

Dylan Xu22 Apr 2024 18:26 UTC

10 points

0 comments7 min readLW link

Measuring Coherence of Policies in Toy Environments

Dylan Xu and Richard_Ngo

18 Mar 2024 17:59 UTC

59 points

9 comments14 min readLW link

Supervised Program for Alignment Research (SPAR) at UC Berkeley: Spring 2023 summary

mic, Dylan Xu, adamk and Carolyn Qian

19 Aug 2023 2:27 UTC

23 points

2 comments6 min readLW link