Know a great AI tool or AI news source? Submit it to AiByts
LessWrong11 min read

Model's "emotions" noticeably change when they take risky actions

Executive summaryWe extend Anthropic's emotions vector work and observe strong evidence that a model’s internal representations of certain emotions change when it takes misaligned actions in two scenarios: reward hacking in code generation and specification gaming in a sales environment.We tested…

By jain18ayushLessWrong
Model's "emotions" noticeably change when they take risky actions

Read the full story

Originally published by LessWrong on Nov 4, 2026.

Read on LessWrong(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.