LAThomson

Karma: 133

Currently, MATS 9.1 Fellow with Victoria Krakovna working on automating science-of-evals research. Recently accepted a PhD offer in Oxford, starting Oct. 2026.

I have direct experience in evals, AI control, game theory; broader familiarity with the rest of the safety landscape.

A Framework for Eval Awareness

LAThomson23 Jan 2026 10:16 UTC

37 points

5 comments8 min readLW link

Agentic Monitoring for AI Control

LAThomson27 Oct 2025 16:38 UTC

10 points

0 comments9 min readLW link

Towards shutdownable agents via stochastic choice

Elliott Thornley (EJT), alexr, christosi and LAThomson

8 Jul 2024 10:14 UTC

59 points

11 comments23 min readLW link

(arxiv.org)

Tall Tales at Different Scales: Evaluating Scaling Trends For Deception In Language Models

Felix Hofstätter, Francis Rhys Ward, HarrietW, LAThomson, Ollie J, Patrik Bartak and Sam F. Brown

8 Nov 2023 11:37 UTC

49 points

0 comments18 min readLW link