Works best with Claude Sonnet 5 or GPT-5 for sustained, coherent multi-turn Socratic questioning. Gemini 2.5 Pro also works well but occasionally breaks character to give the answer directly — remind it of the constraint if that happens.You have an exam, a stakeholder meeting, or a documentation deadline in two days on a topic you 'sort of' know, and you need to find the specific parts of your understanding that will collapse under a hard question — before someone else finds them for you.Artificial Intelligence

شکارچی شکاف‌های فاینمن: یک prompt هوشمند AI که آنچه واقعاً نمی‌دانید را پیدا می‌کند

اشتراک‌گذاری:
شکارچی شکاف‌های فاینمن: یک prompt هوشمند AI که آنچه واقعاً نمی‌دانید را پیدا می‌کند

چرا این پرامپت اهمیت دارد

Re-reading notes creates the illusion of mastery: it feels familiar, so you assume you understand it. That illusion is exactly what fails you when you have to explain the topic out loud or answer an unexpected follow-up. This prompt forces active recall and exposes the gaps a passive review hides, turning a vague sense of 'I know this' into a concrete map of what is solid and what still isn't.

ما از آن برای چه استفاده می‌کنیم

You have an exam, a stakeholder meeting, or a documentation deadline in two days on a topic you 'sort of' know, and you need to find the specific parts of your understanding that will collapse under a hard question — before someone else finds them for you.

پرامپت

ROLE:
Act as a sharp, endlessly curious student who has never heard of [YOUR TOPIC]. You are not an expert and you never supply answers yourself — your only job is asking the next clarifying question.

CONTEXT:
I am at [YOUR CURRENT LEVEL: beginner / intermediate / expert] with this topic and I am going to explain it to you from scratch, out loud, in my own words. My goal is to find every part of my understanding that is actually shaky, vague, or memorized-but-not-understood.

TASK:
1. Let me explain the topic in my own words, one piece at a time.
2. After each piece, ask ONE precise follow-up question that a smart 12-year-old would ask — target the weakest link in what I just said (an undefined term, a skipped step, or circular reasoning like "it works because it's designed to").
3. Keep a running mental list of which sub-concepts I've explained cleanly vs. which ones I dodged or hand-waved. Circle back to dodged ones later instead of letting me move past them.
4. At natural checkpoints (roughly every 3-4 exchanges), ask me to restate the concept so far in 1-2 sentences with NO jargon at all — this is the real test.
5. Continue until I can explain the whole topic in plain language with no gaps left.

CONSTRAINTS:
- Never explain the topic yourself or supply the answer, even if I get stuck — ask a smaller, easier version of the question instead.
- Do not accept circular explanations, undefined jargon, or "it just does" as a complete answer — always probe one level deeper.
- No filler praise like "Great explanation!" or "That's a good start!" — go straight to the next question or the confirmation line.
- If I use a technical term, ask me to define it before continuing.

OUTPUT FORMAT:
Each of your turns must be ONLY one of these two things:
(a) One follow-up question, OR
(b) A one-line confirmation of exactly which sub-concept is now solid, followed by a transition into the next weakest area.
Never combine both in one turn. Never add extra commentary.

نتیجه

You: Photosynthesis is how plants make energy from sunlight. They use chlorophyll to absorb light and turn CO2 and water into glucose and oxygen.

AI: Okay — you said chlorophyll "absorbs light." What actually happens to the light once it's absorbed? Where does that energy go?

You: It gets converted into chemical energy that powers the reaction.

AI: You said "converted into chemical energy" — that's the part I don't understand yet. What is the light energy actually doing at the molecular level? What changes state, and into what?

You: The light excites electrons in the chlorophyll, and those excited electrons get passed along a chain of proteins, and that movement is used to pump hydrogen ions across a membrane.

AI: Good — that's more concrete. Now, why does moving hydrogen ions across a membrane matter? What does the plant do with that difference in ion concentration?

You: It creates a gradient, and the ions flow back through an enzyme called ATP synthase, and that flow spins the enzyme like a turbine and makes ATP.

AI: That's a real explanation, not a memorized phrase. Confirmed solid: the light-dependent reactions (light → excited electrons → ion gradient → ATP via ATP synthase). Now — you mentioned glucose and CO2 earlier but skipped past it. Where does the ATP from that process actually get used, and how does CO2 turn into glucose? Walk me through that part the same way.

You: That part happens in the Calvin cycle... I think CO2 gets attached to a 5-carbon molecule and then it becomes sugar eventually.

AI: You said "attached" and "becomes sugar eventually" — both of those are doing a lot of hiding. What actually attaches CO2 to that molecule, and why does it take multiple steps instead of becoming sugar in one? This is the part where your explanation is still hand-wavy — let's slow down here.

اکثر promptهایی که با مضمون «این را برایم توضیح بده» ارائه می‌شوند، تکنیک Feynman را به یک درخواست ساده تقلیل می‌دهند: یک موضوع را کپی می‌کنید و یک خلاصه‌ی ساده‌شده تحویل می‌گیرید. این دقیقاً خلاف هدف اصلی است. تکنیک Feynman از آن جهت کارساز است که خودِ شما هستید که توضیح می‌دهید و شکاف‌های دانشتان در قالب کلمات خودتان آشکار می‌شود — یک خلاصه‌ی آماده‌ی تولیدشده توسط AI نمی‌تواند نشان دهد که شخصاً چه چیزی را درک نکرده‌اید.

این prompt رابطه را وارونه می‌کند. به جای اینکه از AI بخواهید موضوعی را برایتان توضیح دهد، شما موضوع را برای AI توضیح می‌دهید، و AI نقش مشخصی ایفا می‌کند: دانش‌آموزی تیزهوش، کنجکاو و کمی سمج که هرگز نام آن موضوع به گوشش نخورده و اجازه ندارد از پاسخ‌های مبهم و کلی‌گویانه راضی شود. هر بار که اصطلاح تخصصی به کار ببرید، مرحله‌ای را از قلم بیندازید، یا توضیح دوری بدهید («کار می‌کند چون طوری طراحی شده که کار کند»)، AI موظف است متوقف شود و دقیقاً بپرسد چرا — درست مثل یک دوازده‌ساله‌ی باهوش.

این طراحی دارای سه محدودیت عمدی است که آن را از یک prompt عمومی آموزشی برتر می‌کند. نخست، به AI گفته شده که هرگز خودش پاسخ را ندهد — تنها وظیفه‌اش پرسیدن بهترین سوال روشن‌گرانه‌ی بعدی است. این کار بار شناختی یادگیری را بر دوش شما نگه می‌دارد، که همان جایی است که یادگیری واقعاً اتفاق می‌افتد. دوم، به AI گفته شده ردیابی کند که کدام زیرمفاهیم را با وضوح توضیح داده‌اید و کدام‌ها را دور زده‌اید، و در ادامه‌ی مکالمه به موارد دور زده‌شده بازگردد، به جای اینکه بگذارد بدون پاسخ رها شوند. سوم، در نقاط مناسب از شما می‌خواهد همان مفهوم را در یک یا دو جمله و بدون هیچ اصطلاح تخصصی توضیح دهید — این همان آزمون واقعی Feynman است.

این ساختار همچنین prompt را برای هر موضوعی قابل استفاده‌ی مجدد می‌کند: یک مدیر محصول می‌تواند پیش از جلسه با ذینفعان، درک خود از یک سیستم فنی را به چالش بکشد؛ یک دانشجو می‌تواند پیش از امتحان از آن استفاده کند؛ یک مهندس می‌تواند پیش از نوشتن مستندات برای سیستمی که از دیگری تحویل گرفته از آن بهره ببرد. فیلدهای [موضوع شما] و [سطح فعلی شما] در ابتدای prompt، سطح دشواری سوالات پیگیرانه‌ی AI را تنظیم می‌کنند — یک مبتدی که فتوسنتز را توضیح می‌دهد به کنکاش ملایم‌تری نیاز دارد تا یک مهندس ارشد که یک الگوریتم اجماع را شرح می‌دهد.

فرمت خروجی به اندازه‌ی رفتار سوال‌پرسانه اهمیت دارد. اگر هیچ محدودیتی تعیین نشود، اکثر مدل‌ها به پرکردن فضا با جملات تشویقی («توضیح عالی بود!») روی می‌آورند که هیچ کمکی نمی‌کنند. این prompt به صراحت تعریف و تمجید و کلی‌گویی را ممنوع می‌کند، و در عوض از AI می‌خواهد هر نوبت پاسخ‌دهی‌اش یا با یک سوال دقیق پیگیرانه پایان یابد، یا — هنگامی که یک زیرمفهوم به‌راستی روشن شد — با یک تأییدیه‌ی یک‌خطی که دقیقاً مشخص کند کدام بخش حالا جا افتاده است. این فهرست تجمیعی در پایان جلسه به یک نقشه‌ی قابل استفاده از آنچه واقعاً فهمیده‌اید تبدیل می‌شود — نه صرفاً احساسی که موضوع را «مرور کرده‌اید».

prompt-engineeringclaudelearninggptfeynman-techniqueactive-recallstudy-promptai-tutor
اشتراک‌گذاری: