Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs
by Elliott Thornley, carissacullen, christosi, alexr, LAThomson, and Harry Garland
Update (7 Oct 2026): We reviewed the paper and found that some of our earlier LLM results were partly driven by option-order effects, so we reran the experiments with bigger models, randomized option order, and reasoning before answering. The summary below now reports the updated paper. Summary * Misaligned artificial...
Jun 320