LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2representative citing papers
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.
citing papers explorer
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Chain-of-thought monitorability provides a promising but fragile method for AI safety oversight that developers should actively preserve.