LessWrong24 min read
Is your chatbot less helpful because it thinks you’re a bad person? — Replicating a blogpost
TL;DR [1]A blogpost from a few months ago suggested that LLMs might provide less helpful answers if they see the user as a bad person. I replicate the experiment on more recent models: Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-6.1 Sol, GPT-6.1 Terra, and GPT-6 Luna.
By TeaTieAndHatLessWrong

Read the full story
Originally published by LessWrong on Nov 1, 2026.
Comments
Sign in to join the discussion.