LESSWRONG
LW

323
LAThomson
96100
Message
Dialogue
Subscribe

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!

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No Comments Found
No wikitag contributions to display.
8Agentic Monitoring for AI Control
11h
0
59Towards shutdownable agents via stochastic choice
1y
11
49Tall Tales at Different Scales: Evaluating Scaling Trends For Deception In Language Models
Ω
2y
Ω
0