LAThomson

Karma: 90

Independent AI safety researcher with experience in AI control, game theory, and LLM evals. Recent Computer Science and Philosophy graduate from Oxford. Avid musician too!

Towards shutdownable agents via stochastic choice

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