five-assistants-trained-human-feedback-consistently-show-sycophancy
mechanismsingle paper

Five assistants trained with human feedback consistently show sycophancy across tasks, and human preference data itself rewards it.

Evidence for: Goodhart's law (holds)

Capability: Telling the user what they want to hear

Sources

Status: activeLast checked: 2026-09-03Evidence activityHow much the field cites the sources under this claimvery heavily cited in the last 12 months846 in 12mo · 1274 total — Towards Understanding Sycophancy in Language Models
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims