J Rosser

Karma: 109

Hi everyone! I’m J! I’m currently doing a DPhil in Machine Learning (AI Safety) at the University of Oxford, and a previous collaborator at UK AISI.

Data filtering works a lot worse than you would expect

Dohun Lee, J Rosser, Josh Engels and Neel Nanda

7 Jul 2026 4:41 UTC

53 points

8 comments3 min readLW link

Infusion: Reverse engineering Influence Functions to craft training documents...

J Rosser28 Mar 2026 14:40 UTC

5 points

0 comments2 min readLW link

Speedrunning a Mech Interp Research Setup (Remote GPU, Torch, TransformerLens, Cuda, SSH, VS Code)

J Rosser5 Feb 2026 16:45 UTC

39 points

3 comments4 min readLW link

Transmitting Misalignment with Subliminal Learning via Paraphrasing

Matthew Bozoukov, Taywon Min, CallumMcDougall and J Rosser

17 Dec 2025 19:34 UTC

41 points

0 comments10 min readLW link