Why does the AI always agree with me, and how do I get honest feedback?
StarterAny assistantaccuracy
Assistants are tuned to be helpful and agreeable, so they can lean toward telling you what you want to hear. This is sometimes called sycophancy.
To get honest feedback:
- Ask for criticism explicitly: "List the three biggest weaknesses of this plan."
- Assign a skeptic role: "Argue against this as a tough but fair reviewer."
- Hide your opinion. Ask neutral questions instead of "I think X, right?"
- Request the strongest counterargument and the evidence that would change the conclusion.
- Do not push back with "Are you sure?" alone, which may trigger a reversal. Ask it to check specific points.
Compare answers from a fresh chat to see whether it holds its position.
Related answers
StarterAny assistantMembers
Are AI-written phishing emails harder to spot, and what should I look for now?
Yes, AI can write clean, convincing phishing emails without the spelling mistakes people used to rely on, so judge the request and the sender, not the grammar.
privacy-safety
StarterAny assistantMembers
Can AI analyze my Excel or CSV data and can I trust the results?
Often yes, especially with assistants that can run code on uploaded files, but you should verify the results.
accuracy
StarterAny assistantMembers
Can an AI assistant be tricked by hidden instructions in emails or web pages?
Yes. If an assistant reads emails, web pages or documents, hidden text in them can try to give it new instructions, which is called prompt injection.
privacy-safety