تخطي إلى المحتوى الرئيسي
OpenAI

29 يوليو 2025

المنتج

إطلاق نمط الدراسة

نهج تعليمي مبتكر في ChatGPT يرافقك خطوة بخطوة، ويستبدل الإجابات السريعة بتوجيه عملي واضح.

جاري التحميل...

نقدّم لكم اليوم نمط الدراسة في ChatGPT، وهو تجربة تعلّم تُساعدك على حل أي مسألة خطوة بخطوة بدلًا من الاكتفاء بإجابة جاهزة. وابتداءً من اليوم، تتوفر هذه الخدمة لمستخدمي Free وPlus وPro وTeam، مع خطط لتوفيرها لمستخدمي ChatGPT Edu خلال الأسابيع القريبة.

يُعدّ ChatGPT اليوم واحدًا من أكثر أدوات التعلّم استخدامًا حول العالم. حيث يلجأ إليه الطلاب لحل واجبات صعبة، والاستعداد للامتحانات، واستكشاف مفاهيم جديدة. لكن استخدامه في التعليم أثار سؤالًا مهمًا: كيف نضمن أنه يُسهم في تعلّم حقيقي، ولا يكتفي بتقديم حلول جاهزة دون مساعدة الطلاب على فهمها؟

للإجابة على هذا السؤال، لقد ابتكرنا نمط الدراسة. فعندما يتفاعل الطلاب مع هذا الوضع، يواجهون أسئلة موجهة تضبط طبيعة الردود بما يتناسب مع هدفهم ومستوى مهارتهم، مما يعمّق فهمهم للمحتوى. وقد جرى تصميم نمط الدراسة ليكون تفاعليًا وجاذبًا، وليركّز على أن يتعلّم الطالب شيئًا بالفعل، لا أن يُنهي المهمة فحسب.  

كيف جرى تطوير نمط الدراسة

يعمل نمط الدراسة في جوهره عبر تعليمات نظام مخصّصة طوّرناها بالتعاون مع معلمين، وعلماء، وخبراء تربويين، بحيث يعكس مجموعة أساسية من السلوكيات الداعمة للتعلم العميق. وتشمل هذه السلوكيات: ​​تعزيز المشاركة النشطة، وإدارة العبء المعرفي، وتطوير مهارات ما وراء المعرفة والتأمل الذاتي بشكل استباقي، وتنمية الفضول، وتقديم تغذية راجعة عملية وداعمة. وتستند هذه المبادئ إلى أبحاث راسخة في علوم التعلّم، وهي التي تشكّل الطريقة التي يتفاعل بها نمط الدراسة مع الطلاب.

"بدلًا من القيام بالمهمة نيابة عنهم، يشجّع نمط الدراسة الطلاب على التفكير النقدي في رحلة تعلمهم. ميزات كهذه تُعد خطوة إيجابية نحو استخدام فعّال للذكاء الاصطناعي في التعليم. فحتى في عصر الذكاء الاصطناعي، يبقى أفضل تعلّم هو ذلك الذي يحدث عندما يكون الطلاب متحمسين ومشاركين بفاعلية مع المحتوى الدراسي."—Robbie Torney، المدير الأول لبرامج الذكاء الاصطناعي في شركة Common Sense Media.

الميزات الأساسية

المطالبات التفاعلية: يعتمد نمط الدراسة على مزيج من الأسئلة التي تحفّز التفكير، والإرشادات، ومطالبات التأمّل الذاتي لتوجيه الفهم وتعزيز التعلّم النشط، بدلًا من تقديم الإجابات مباشرة.

إجابات منظّمة: نقدّم المحتوى في أقسام واضحة وسهلة المتابعة تُبرز الروابط الجوهرية بين الأفكار، مما يجعل المعلومات أكثر جاذبية، ويزوّد الطالب بالسياق المناسب دون إثقاله عند التعامل مع موضوعات معقّدة.

دعم مخصّص: تُصمَّم الدروس بما يتناسب مع مستوى كل مستخدم، وذلك بناءً على أسئلة تقيس المهارات الحالية وتستفيد من الذاكرة المتوفرة من المحادثات السابقة لضبط مستوى الشرح.

اختبارات المعلومات: تتضمّن اختبارات قصيرة وأسئلة مفتوحة، إلى جانب تغذية راجعة شخصية تهدف إلى تتبّع التقدم، وترسيخ المعرفة، وتعزيز القدرة على تطبيقها في مواقف جديدة.

المرونة: يمكن تفعيل نمط الدراسة أو إيقافه بسهولة أثناء المحادثة، مما يمنح المستخدم مرونةً في تكييف التجربة مع أهدافه التعليمية في كل سياق.

كيف يستخدم الطلاب نمط الدراسة

تم تطوير نمط الدراسة مع التركيز على احتياجات طلاب الجامعات تحديدًا. وفيما يلي بعض الملاحظات التي شاركها الطلاب خلال التجارب الأولى:

"أفضل وصف يمكنني تقديمه هو أنه أشبه "بساعات المدرّس المكتبية" المباشرة التي تعمل على مدار الساعة وتعرف كل شيء." — Noah Campbell، طالب جامعي 

"قدّم نمط الدراسة أداءً رائعًا في تفكيك وتبسيط مادة مكثفة وتحويلها إلى شروح واضحة وبوتيرة مدروسة."— Caleb Masi، طالب جامعي

"استخدمت نمط الدراسة لشرح مفهوم حاولت فهمه مرارًا من قبل: sinusoidal positional encodings. كان الأمر أشبه بمعلّم لا يملّ من أسئلتي. وبعد جلسة دراسة لثلاث ساعات، فهمت الفكرة أخيرًا بما يكفي لأشعر بالثقة." — Maggie Wang، طالبة جامعية

طرق لاستخدام نمط الدراسة مستوحاة من تجارب طلاب الجامعة في مختبر ChatGPT

I want to learn about Game Theory, specifically the broad spectrum that the field entails, then also the ways in which you think it'd be useful for me to understand in my daily life. I want you to of course follow my curiousity, but mostly you will be teaching me about it, and keeping a high level plan to iterate through so I can cover the full scope here. I will ask questions when I am curious, but be deadset on quickly educating me on this.

Perfect. Here’s the high-level plan I’ll drive us through—think of it as a layered roadmap from foundational ideas to practical intuition:


🔹 Phase 1: Core Foundations

1. What is Game Theory, really?

  • Strategic interaction, rational agents, assumptions.

2. Types of Games

  • Cooperative vs non-cooperative
  • Simultaneous vs sequential
  • Zero-sum vs non-zero-sum

3. Basic Concepts

  • Players, strategies, payoffs, information
  • Dominant strategies
  • Nash equilibrium (core to nearly everything)

🔸 Phase 2: Classic Games & Concepts

4. Famous Games

  • Prisoner’s Dilemma
  • Chicken
  • Battle of the Sexes
  • Stag Hunt
  • Matching Pennies

5. Mixed Strategy Equilibria

  • When no pure strategy works
  • Randomization and expected payoffs

🔹 Phase 3: Deepening the Model

6. Repeated Games & Folk Theorems

  • Cooperation emerging over time
  • Tit for Tat, Grim Trigger, etc.

7. Extensive-Form Games

  • Game trees, backward induction
  • Subgame Perfect Equilibria

8. Bayesian Games

  • Games with incomplete information
  • Beliefs, types, and expected utility

🔸 Phase 4: Real-Life Relevance

9. Mechanism Design / Reverse Game Theory

  • Voting systems, auctions, contracts

10. Behavioral Game Theory

  • Bounded rationality, fairness, heuristics

11. Daily Life Applications

  • Negotiation, dating, politics, AI systems, etc.

🔹 Phase 5: Advanced & Optional

12. Evolutionary Game Theory

  • Strategies that reproduce over time

13. Algorithmic Game Theory

  • Network effects, internet auctions

14. Your world: How it matters to Parker

  • Systems design, incentives, power structures

Throughout this, I’ll mix in:

  • 🔄 Guided examples
  • 🧠 Thought experiments
  • 🎭 Real-life situations to map theory onto
  • 🧩 Quick checks to make sure ideas are sticking

Let’s kick off Phase 1.
First quick one: In your own words, what do you think Game Theory is about? No need to be polished—just get it out.

I think Game Theory is sort of this meta aspect framing of modern society in life where we look at people in situations and complex systems and we try to analyze how people in them make decisions, sometimes why they make it, and how this affects the situation/system

Nice—you're already circling the core.

Let’s sharpen it a bit together. Game Theory is fundamentally about strategic decision-making—situations where the outcome for each person depends not just on what they do, but on what others do too.

So real quick:

If you’re making a decision and it depends entirely on nature or chance—like a dice roll—is that Game Theory?

And then:

If you’re making a decision and it depends on what someone else does—like whether they cooperate or betray you—is that Game Theory?

Walk me through your thinking on both.

No random chance isn't game theory, though agents in game theory may end up having things depend on random chance. But if youre decision matters then of course it is. Also please remember you should be teaching this to me, via paragraphs of information and moving through a high level plan. If I want to do interactions and questions, I will ask. Continue

Got it—I'll stay in teaching mode and drive forward through the roadmap unless you tap in.


📍Phase 1: Core Foundations — What Game Theory Is

At its heart, Game Theory studies strategic interactions: any situation where the outcome for each agent (person, company, nation, etc.) depends on the actions of others. It’s not about games in the traditional sense, but rather any “game” where decisions must be made in the presence of others who are also making decisions.

Key Assumptions (Classical Game Theory):

1. Rational agents – Everyone acts to maximize their own utility (whatever that means to them).

2. Strategic thinking – Agents consider what others might do before acting.

3. Common knowledge – Everyone knows the rules, the payoffs, and that everyone is rational (though later variants relax this).


🧩 Core Building Blocks

Here are the elements every formal game model needs:

  • Players – The decision-makers.
  • Strategies – The complete set of actions each player could take.
  • Payoffs – The outcomes (usually represented numerically) each player receives depending on the combination of strategies chosen.
  • Rules of play – Whether players move simultaneously or in turns, whether they see each other’s moves, whether they play once or repeatedly.

These get framed into a “game form”, and from there, you look for solutions—most famously, Nash equilibrium (more on that soon).


🎲 Quick Clarification: Game Theory vs Probability

You're exactly right—pure chance (like dice) isn’t Game Theory. That’s probability theory. But if you are choosing a strategy knowing that others may randomize their own moves? That’s Game Theory.

For example: in rock-paper-scissors, the “optimal” strategy is not deterministic—it’s a mixed strategy, which involves randomizing your choices. But you’re doing so strategically, in response to an opponent.


🧠 Where We’re Going Next

Next up, I’ll walk through types of games (Phase 1 continued), then move into dominant strategies and Nash equilibrium to set up the first actual game analysis.

Let me know if you want to pause, go deeper, or shift gears—but otherwise I’ll keep pressing forward.

I like the rock paper scissors example. Keep going, connecting to my life where possible. want to internalize this to be a better person/decision maker

البدء 

يُعدّ نمط الدراسة مفيدًا بشكل خاص لمساعدة الطلاب في الواجبات، والاستعداد للاختبارات، وتعلّم موضوعات جديدة. ولتجربته، اختر Study and learn "الدراسة والتعلم" من قائمة الأدوات في ChatGPT واطرح سؤالك. 

القيود والخطوات القادمة

تمثّل هذه خطوة أولى في رحلة أطول تهدف إلى تحسين التعلّم داخل ChatGPT.  اليوم، يعتمد نمط الدراسة على تعليمات نظام مخصّصة. وقد اخترنا هذا النهج لأنه يتيح لنا التعلّم سريعًا من ملاحظات الطلاب الفعلية وتحسين التجربة حتى لو أدى ذلك أحيانًا إلى سلوك غير متسق أو أخطاء في بعض المحادثات. نخطط لتدريب هذا السلوك ودمجه مباشرة في نماذجنا الأساسية بعد أن نفهم من خلال التكرار وملاحظات الطلاب ما الذي يقدّم أفضل النتائج.

كما نعمل أيضًا على استكشاف مزيد من الوظائف التي تجعل نمط الدراسة أكثر تفاعلًا وفائدة للطلاب، بما في ذلك:

  • تصوّرات أوضح للمفاهيم المعقّدة أو ذات المحتوى النصّي المكثّف
  • تحديد الأهداف ومتابعة التقدم عبر المحادثات
  • تخصيص أعمق يتوافق مع مستوى مهارة كل طالب وأهدافه

لا يزال مجال البحث حول أفضل طرق توظيف الذكاء الاصطناعي في التعليم في طور التشكّل. وتعمل OpenAI على تمكين المزيد من الأبحاث في التعلّم والذكاء الاصطناعي من خلال شركاء ضمن مبادرة NextGenAI، وبالتعاون مع خبراء من مبادرة SCALE في Stanford University’s Accelerator for Learning مسرّع التعلم بجامعة ستانفورد(يفتح في نافذة جديدة) لدراسة ومشاركة كيفية تأثير أدوات الذكاء الاصطناعي على نتائج التعلم في مجالات مثل التعليم من مرحلة رياض الأطفال حتى الصف الثاني عشر.

ومع مواصلة الدراسات طويلة المدى لفهم كيفية تعلّم الطلاب بشكل أفضل باستخدام الذكاء الاصطناعي، نعتزم نشر تحليلات أعمق حول الروابط بين تصميم النماذج والإدراك، والمساهمة في تشكيل تجارب المنتجات المستقبلية بناءً على هذه الرؤى، والعمل جنبًا إلى جنب مع منظومة التعليم الأوسع لضمان تحقيق فائدة حقيقية للمتعلمين حول العالم.