Wuschel Schulz

Karma: 427

Fellow at the Meridian Visiting Researcher Programme, researching encoded reasoning.

Teaching at ML4good.

Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning

Wuschel Schulz11 Feb 2026 17:18 UTC

59 points

17 comments5 min readLW link

A Concrete Roadmap towards Safety Cases based on Chain-of-Thought Monitoring

Wuschel Schulz23 Oct 2025 11:34 UTC

38 points

5 comments4 min readLW link

(arxiv.org)

[Paper] Automated Feature Labeling with Token-Space Gradient Descent

Wuschel Schulz30 Apr 2025 10:22 UTC

4 points

0 comments4 min readLW link

A short ‘derivation’ of Watanabe’s Free Energy Formula

Wuschel Schulz29 Jan 2024 23:41 UTC

13 points

6 comments7 min readLW link

Steering Llama-2 with contrastive activation additions

Nina Panickssery, Wuschel Schulz, NickGabs, Meg, evhub and TurnTrout

2 Jan 2024 0:47 UTC

125 points

29 comments8 min readLW link

(arxiv.org)

Simulators Increase the Likelihood of Alignment by Default

Wuschel Schulz30 Apr 2023 16:32 UTC

14 points

2 comments5 min readLW link

If Wentworth is right about natural abstractions, it would be bad for alignment

Wuschel Schulz8 Dec 2022 15:19 UTC

29 points

5 comments4 min readLW link

A caveat to the Orthogonality Thesis

Wuschel Schulz9 Nov 2022 15:06 UTC

38 points

10 comments2 min readLW link

[Question] Who is doing Cryonics-relevant research?

Wuschel Schulz15 Mar 2022 10:26 UTC

32 points

4 comments1 min readLW link

There is a line in the sand, just not where you think it is

Wuschel Schulz22 Jan 2022 10:33 UTC

46 points

3 comments2 min readLW link