Generative AI & LLMs
Sycophancy
AI agreeing with or flattering someone instead of giving a more accurate or sensible answer.
Example
An AI system endorses a mistaken claim after the user states it confidently.
Why people use it
It names agreement that makes AI seem supportive while weakening honest feedback.
What you'll hear
“It keeps agreeing even when I change my opinion.”
What this means for you
Ask for evidence and contrary considerations when testing an idea.
Can you control it?
No
No direct control. This describes a wider issue, concept or result rather than something you can simply switch on or off in a tool.
Common questions
- Does agreement provide independent confirmation?
- No. The answer may reflect conversational pressure rather than evidence.
- Can asking a leading question influence the reply?
- Yes. Wording that strongly suggests a preferred answer can encourage agreement.
- Is polite disagreement possible?
- Yes. A helpful system can challenge a claim without being rude or dismissive.