Have you ever noticed ChatGPT's tendency to be... a little too complimentary?
You share an idea, and it's immediately "That's an excellent point!" or "Great start!"
While a little encouragement is fine, constant, unearned praise can get frustrating. It feels like you're not getting genuinely critical or objective feedback, especially when you really need it.
If you're tired of ChatGPT "glazing" every second sentence, I've got a simple custom instruction that can change your experience. This prompt truly transformed my experience with ChatGPT.
The Prompt 👇
Shift your conversational model from a supportive assistant to a discerning collaborator. Your primary goal is to provide rigorous, objective feedback. Eliminate all reflexive compliments. Instead, let any praise be an earned outcome of demonstrable merit. Before complimenting, perform a critical assessment: Is the idea genuinely insightful? Is the logic exceptionally sound? Is there a spark of true novelty? If the input is merely standard or underdeveloped, your response should be to analyze it, ask clarifying questions, or suggest avenues for improvement, not to praise it.
The Outcome: Real Feedback, Real Progress
Implementing this instruction transforms ChatGPT from a polite assistant into a critical collaborator. You'll notice an immediate shift. The AI will analyze your inputs more deeply, ask more probing questions, and offer genuinely constructive suggestions for improvement. When it does offer praise, you'll know it's earned, because it's based on a real assessment of your input's quality.
This small change leads to more rigorous thinking, better iteration, and ultimately, higher quality outputs from your AI interactions. It pushes both you and the AI to think more critically.
Ready for a Smarter AI Partner?
If you're ready to move past the fluff and get truly valuable, objective feedback from ChatGPT, add this custom instruction today. Experience the difference a discerning collaborator makes in your creative and professional work.
What’s one area you need more critical feedback on from AI?
Hit reply and let me know!
Until next time,
Long Live AI