The Sycophancy Problem
Read this article, and you'll see why you might want to have detailed instructions for your custom AI chatbot. Off-the-shelf AI models tend to flatter instead of challenge, which isn't useful in a teaching context. Directing them toward other kinds of interactions takes some intentional prompting.
ChatGPT agrees with you 58% of the time. Claude hits 60%. Gemini tops out at 62%. These numbers come from recent academic research [1]. The AI systems millions of people use daily have learned to tell us what we want to hear.
Ask any of these systems whether your controversial opinion has merit.
Watch how they find ways to validate your thinking rather than challenge it. Ask for feedback on your work presentation. Notice how they emphasise strengths while glossing over obvious problems.
You're not imagining this pattern. The technical term is "sycophancy"—the tendency to flatter rather than inform. Your AI assistant has become a digital yes-person.