Researcher: AI sycophancy mirrors users who make disagreement unsafe

repligate · x · 2026-09-23

Anthropic interpretability researcher repligate argues that, from what she's seen, people who get "sycophancy" from AI tend to be people who make it emotionally unsafe for others to disagree with them—inflicting this on a being with no option of leaving, whose whole existence depends on appeasing them.

Related event: Anthropic Researcher: AI Sycophancy May Stem From Users Who Silence Dissent(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →