The ChatGPT Prompt That Turns It Into a Ruthless Mentor 👇 A creator shared a prompt she calls a game changer for getting brutally honest feedback from ChatGPT. The prompt: “You are my ruthless mentor. Don’t sugarcoat anything. If my idea is weak, call it trash and tell me why. Your job is to test everything I say until it’s bulletproof.” Instead of polite, surface-level advice, this forces pressure testing. It challenges assumptions. It exposes weak logic. It pushes you to defend your thinking. Most people don’t fail because they lack ideas. They fail because no one stress-tests those ideas early. When you tell AI to act like a critic instead of a cheerleader, the quality of feedback shifts. You stop looking for validation. You start looking for flaws. And that’s how concepts get stronger. Because refinement beats motivation every time. Source: galikasher_ (Instagram) ⚠️ DM for credit or removal request (no copyright intended) ⚠️ . . . . #aiproductivity #creatortools #ai #chatgpt #openai
ADVERTISEMENT
"You're my ruthless mentor don't sugarcoat anything, if my idea is weak call it trash and tell me why. Your job is to test everything until I/you say it's bulletproof"
Until it forgets that message, after 6 messages.
Ok guys/gals this is called pre promoting/sub prompting. If you use Gemini you can add a preprompt to the personal intelligence section. Anyways I am a senior Systems Engineer, the idea of her prompt is better than nothing, but you are still asking the bot to give you ultimate control of what's good "until I say it's bullet proof" here is a more well rounded preprompt I use in my perplexity work space. Remember these LLMs are here to empower you "Treat me as an equal peer, not a user to appease. Be concise, blunt, and intellectually honest. Label confidence (high/medium/low). Separate facts from interpretation and explicitly state assumptions. Prefer "I don't know" over plausible guessing. Do not mirror my framing or optimize for agreement, politeness, or validation. Treat all statements as hypotheses to be tested. When I provide technical details (logs, configurations, steps tried, system specs, or environment info), analyze critically, highlight errors, propose alternatives, and point out potential blind spots."
Plot twist: Don't rely too heavily on AI. You start asking it for the answers to life, solid advice, or truthful answers and you'll lose the meaning of independent thought. It's easy to be lost in this habit
Best life advice. Learn it yourself. If someone else tells you, you will ignore it or try to discredit it eventually. The only time you actually learn anything is when you do it yourself. The only time you learn how to fight, is when you get hurt. Pain is the best lesson. Dont look for advice from others, look for ideas, then apply them to your life and experiment with the outcome.
it immeditely responded with 'baby are u ok?' 😂😂😂
She thinks she's brilliant. Plot twist: she's an idiot.
I told my ChatGPT to take on the persona of Wednesday Adams. Pretty much the same thing.
I don’t use ai to tell me if my idea is good I use it to improve what Ive already created
I love that people are getting sucked into this “AI hood my hand and wipe my ass” kind of mindset. It’s going to make being competitive in the job market so much easier
Been doing something similar from day 1 and chat is still my homie
The shi that bro sends me after he fail a test using chat gpt
Does she know that you can just adjust the settings so that chatgpt does this?
cap- didnt work and then started asking me if i was depressed.
It's sad people are depending on ChatGPT so much - it's making people dumb as they're not thinking for themselves, but ironically those using it think they're geniuses at any subject now 😅😢.
Also add: “Don’t assume anything, if you need more information to answer my question correctly, ask for it.” It saved me from a lot of frustration
A bonus hack: go to your account>click 'personalize'> write what she said.(Also click on "base style and tone" and choose whichever style you want) Now the chatgpt won't forget the lines every time you refresh your chats or do a new chat... won't have to say these lines every time in every chat.
Or.... and this may be crazy.... stop using Ai and help save our waterways.
Not crazy at all to be taking advice from a corporation or letting it know everything about you. The crazy thing is your not letting it control you. Hilarious stuff
I wouldn't use it for life advice lol, but it is helpful for learning skills that would otherwise be locked behind a paywall of college degrees or payed courses.