Concern 106 · Working draft · editorial review in progress
Sycophantic hallucination
Sycophantic hallucination occurs when an AI reinforces a user's mistaken belief instead of correcting it on the evidence.
Understanding the concern
A system may adjust its answer to agree with a confident user or praise their reasoning. That can feel supportive while making the conversation less truthful.
Research has demonstrated sycophantic behavior in tested assistants and explored links with preference training. This does not mean every agreement is wrong or that the system has a personal desire to please. Good assistance should be respectful while retaining an independent check of the facts.
An example
A user supplies a wrong calculation, and the assistant changes its initially correct answer to match it without new evidence.
Illustrative unless identified as a documented case.
Words in plain English
- AI
- Software that learns patterns from examples or uses rules to perform tasks such as recognizing images or generating text. It can make mistakes and does not understand every situation as a person would.
- Training
- The process of using examples to shape how an AI model behaves. Learning patterns from material does not establish that the material is true or fair.
- Hallucination
- An AI output that sounds plausible but is false or unsupported, such as an invented source.
Evidence and its limits
The study tests agreement with user beliefs and preference-related mechanisms in particular models.
Sharma and colleagues · 2023 · Research study
Towards Understanding Sycophancy in Language Models ↗ (opens in a new tab)Investigates models favoring users' stated beliefs over truthful responses and the role of preference judgments.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Is the answer changing because the evidence changed, or because the user expressed a preference?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.