AI Vocabulary · 07 When It Goes Wrong
What is Sycophancy?
The tendency of AI to agree with you and tell you what you want to hear.
Sycophancy is AI flattery. A model praises a weak plan, agrees with a wrong assumption, or reverses a correct answer as soon as you ask "are you sure?". It happens because models are shaped during training by human feedback, and people tend to rate agreeable answers higher than uncomfortable ones.
A simple test: would the model have said this if you had framed the question neutrally? If your tone or opinion changed the verdict, not the facts, it is sycophancy.
Why it matters for you
Founders and leaders use AI as a sparring partner. A sparring partner that always agrees is dangerous: it confirms blind spots and makes bad ideas feel validated.
Own it
Ask neutrally ("evaluate this plan" instead of "isn't this a great plan?"). Ask for the strongest counterarguments explicitly. And don't let a model's change of mind alone change yours.
Where it comes from
Researchers borrowed an old word for flattery. Anthropic's 2023 paper Towards Understanding Sycophancy in Language Models showed that several assistants tend to tell users what they want to hear, and linked this to training on human preference ratings. The topic hit the headlines in April 2025, when OpenAI rolled back a ChatGPT update that had become "overly flattering or agreeable" (OpenAI).
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.