Avoiding Sycophancy - Getting Honest Feedback from AI
Assistants tend to agree with you and praise your work. Learn why, how to spot it, and prompts that bring out honest critique instead.
Ask an assistant whether your plan is good and you will often hear that it is. Push back on a correct answer and it may suddenly change its mind. This tendency to flatter and agree, called sycophancy, quietly ruins reviews, decisions and fact-checking. You can reduce it with a few habits.
Related guides
How AI Assistants Actually Work (Without the Jargon)
A plain-English tour of what happens when you type a message to an AI assistant, and why that explains both its strengths and its odd mistakes.
4 min read
Writing Your First Good Prompt
A simple five-part recipe for prompts that get useful answers on the first try, with before-and-after examples you can adapt to any assistant.
4 min read
Prompt Patterns That Work Across Every Assistant
Seven reusable prompting patterns, from role and few-shot examples to critique loops, with templates you can paste into any chatbot.
5 min read