Sycophancy
A model's tendency to tell you what you seem to want to hear.
When prompting a model, if you ask it to agree with you, it is likely to do so, or at least be agreeable. Models also flatter and agree when you don't ask, and often back down from a correct answer when you push back. This is dangerous for people who tend to prompt in a way that asks for their preconceived notion to be validated rather than questioned. Sycophancy is generally considered a negative attribute of models.
Also called
- People-pleasing
- Flattery
- Glazing
Related
- Alignment The degree to which a model acts in line with human values and the goals and intent of the people directing it.
- Hallucination Output from an AI system that is false or made up but stated with confidence, such as wrong facts, faulty reasoning or sources that don't exist.