ข้ามไปยังเนื้อหาหลัก
OpenAI

29 กรกฎาคม 2568

ผลิตภัณฑ์

แนะนำโหมดการเรียนรู้

วิธีการเรียนรู้รูปแบบใหม่ใน ChatGPT ที่ให้คำแนะนำแบบเป็นขั้นตอนแทนที่จะบอกคำตอบเลย

กำลังโหลด…

วันนี้เราขอแนะนำโหมดการเรียนรู้ใน ChatGPT ที่มาพร้อมรูปแบบการเรียนรู้ที่ช่วยให้คุณทำความเข้าใจและแก้ปัญหาแบบเป็นขั้นตอน ไม่ใช่เพียงแค่ให้คำตอบ ตั้งแต่วันนี้เป็นต้นไปผู้ใช้ที่ลงชื่อเข้าใช้ผ่านแพ็กเกจ Free, Plus, Pro, และ Team สามารถใช้งานโหมดนี้ได้แล้ว และจะเปิดให้ใช้งานใน ChatGPT Edu ในอีกไม่กี่สัปดาห์ข้างหน้า

ChatGPT กำลังกลายเป็นหนึ่งในเครื่องมือการเรียนรู้ที่มีการใช้งานมากที่สุดในโลก ผู้เรียนหันมาพึ่ง ChatGPT ในการช่วยทำการบ้านที่ยากๆ เตรียมสอบ แล้วก็ลองเรียนรู้สิ่งใหม่ๆ แต่การนำไปใช้ในด้านการศึกษาก็ทำให้เกิดคำถามสำคัญว่า เราจะมั่นใจได้อย่างไรว่าเครื่องมือนี้ช่วยสนับสนุนการเรียนรู้จริงๆ ไม่ใช่แค่ให้คำตอบโดยไม่ทำให้นักเรียนเข้าใจเนื้อหา

เราจึงสร้างโหมดการเรียนรู้เพื่อช่วยตอบคำถามนี้ เมื่อผู้เรียนใช้โหมดการเรียนรู้ ผู้เรียนจะพบกับคำถามชี้นำ ซึ่งจะปรับการตอบกลับให้สอดคล้องกับวัตถุประสงค์และระดับทักษะของผู้เรียน ช่วยให้เกิดความเข้าใจที่ลึกซึ้งยิ่งขึ้น โหมดการเรียนรู้ได้รับการออกแบบมาให้มีความน่าสนใจและมีการสร้างปฏิสัมพันธ์ เพื่อช่วยให้ผู้เรียนเกิดการเรียนรู้ ไม่ใช่แค่ทำงานให้เสร็จๆ ไป  

ที่มาของการพัฒนาโหมดการเรียนรู้

เบื้องหลังการทำงานของโหมดการเรียนรู้นั้นได้รับการขับเคลื่อนด้วยคำสั่งระบบที่ปรับแต่งเอง ซึ่งเราเขียนขึ้นโดยร่วมมือกับครูผู้สอน นักวิทยาศาสตร์ และผู้เชี่ยวชาญด้านการสอน เพื่อให้สะท้อนถึงชุดพฤติกรรมหลักที่สนับสนุนการเรียนรู้เชิงลึกซึ่งรวมถึง การส่งเสริมการมีส่วนร่วม การจัดการภาระทางปัญญา การพัฒนาความตระหนักรู้ในตนเองและการทบทวนตนเอง การส่งเสริมความอยากรู้อยากเห็น และการให้ข้อเสนอแนะที่นำไปปฏิบัติได้จริงและเป็นประโยชน์ พฤติกรรมเหล่านี้มีพื้นฐานมาจากการวิจัยที่ยาวนานในศาสตร์แห่งการเรียนรู้ และเป็นตัวกำหนดว่าโหมดการเรียนรู้ควรโต้ตอบผู้เรียนอย่างไร

"โหมดการเรียนรู้จะส่งเสริมให้นักเรียนคิดวิเคราะห์เกี่ยวกับการเรียนรู้ของตนเองแทนที่จะทำงานแทนผู้เรียนให้เสร็จ คุณสมบัติเหล่านี้เป็นก้าวสำคัญสู่การใช้ AI เพื่อการเรียนรู้อย่างมีประสิทธิภาพ แม้จะเป็นยุคแห่ง AI แต่การเรียนรู้ที่ดีที่สุดจะเกิดขึ้นก็ต่อเมื่อ ผู้เรียนรู้สึกกระตือรือร้นในการมีส่วนร่วมกับเนื้อหาบทเรียน —Robbie Torney ผู้อำนวยการอาวุโสของโปรแกรม AI จาก Common Sense Media

ฟีเจอร์หลัก

คำสั่งเชิงปฏิสัมพันธ์: ผสมผสานการตั้งคำถามแบบเชิงวิพากษ์ การให้คำใบ้ กระตุ้นให้ผู้เรียนคิดเอง เพื่อช่วยให้นักเรียนเข้าใจและเรียนรู้อย่างมีส่วนร่วม แทนที่จะให้คำตอบตรงๆ ทันที

การตอบแบบมีโครงสร้าง: แบ่งข้อมูลเป็นส่วนๆ ให้อ่านเข้าใจง่าย เน้นความเชื่อมโยงสำคัญระหว่างหัวข้อเพื่อทำให้ข้อมูลน่าสนใจด้วยบริบทที่พอเหมาะ ช่วยให้รู้สึกไม่หนักเกินไปแม้เป็นเรื่องซับซ้อน

การสนับสนุนแบบเฉพาะบุคคล: บทเรียนได้รับการปรับให้เหมาะสมกับระดับของผู้ใช้ โดยอ้างอิงจากคำถามที่ใช้ประเมินทักษะและจำข้อมูลมาจากการคุยก่อนหน้า

การตรวจสอบความรู้: ใช้แบบทดสอบและคำถามปลายเปิด พร้อมคำแนะนำเฉพาะบุคคลเพื่อติดตามความก้าวหน้า ช่วยให้ผู้เรียนจำความรู้ได้และนำไปปรับใช้กับสถานการณ์ใหม่ๆ

ความยืดหยุ่น: สามารถเปิดและปิดโหมดการเรียนรู้ระหว่างการสนทนาได้อย่างง่ายดาย ทำให้คุณปรับเปลี่ยนการเรียนรู้ตามเป้าหมายของแต่ละการสนทนาได้อย่างยืดหยุ่น

ผู้เรียนใช้โหมดการเรียนรู้อย่างไรบ้าง

โหมดการเรียนรู้สร้างขึ้นโดยคำนึงถึงนักศึกษาระดับมหาวิทยาลัย ข้อติชมที่เราได้รับจากผู้เรียนระหว่างทดลองใช้ช่วงแรก:

"พูดง่ายๆ ก็คือ มันเหมือนมีอาจารย์ที่พร้อมตอบตลอดเวลา แบบตลอด 24 ชั่วโมง และรอบรู้ทุกเรื่อง" —Noah Campbell นักศึกษาวิทยาลัย 

"โหมดเรียนรู้ช่วยอธิบายเรื่องยากๆ ให้เข้าใจง่ายและเป็นขั้นตอนได้ดีมากเลย และก็มีจังหวะการอธิบายที่เหมาะเจาะ  " —Caleb Masi นักศึกษาวิทยาลัย

"ฉันเอาโหมดเรียนรู้มาทดสอบ ให้ช่วยสอนเรื่องที่ผมเคยพยายามเรียนซ้ำๆ แต่ยังไม่เข้าใจ นั่นคือการเข้ารหัสตำแหน่งโดยใช้ฟังก์ชันไซน์ (Sinusoidal Positional Encodings) มันเหมือนเป็นติวเตอร์ที่ไม่เหนื่อยกับการตอบคำถามของฉันเลย หลังจากเรียนอยู่ 3 ชั่วโมง ในที่สุดฉันก็ทำความเข้าใจเรื่องนี้ได้ดีจนรู้สึกมั่นใจ"—Maggie Wang นักศึกษาวิทยาลัย

วิธีการใช้โหมดการเรียนรู้ที่ได้รับแรงบันดาลใจจากนักศึกษามหาวิทยาลัยจากห้องแล็บ 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

เริ่มต้นใช้งาน

โหมดการเรียนมีประโยชน์มากสำหรับการช่วยทำการบ้าน การเตรียมสอบ และการเรียนรู้หัวข้อใหม่ๆ หากต้องการทดลองใช้งาน ให้เลือกเมนู "ศึกษาและเรียนรู้" จากเครื่องมือใน ChatGPT แล้วถามคำถามได้เลย 

ข้อจำกัดและก้าวต่อไป

นี่คือก้าวแรกบนเส้นทางที่ยาวไกลเพื่อพัฒนาการเรียนรู้ใน ChatGPT  ทุกวันนี้โหมดเรียนรู้ทำงานโดยใช้คำสั่งระบบที่สร้างขึ้นเอง เราเลือกแนวทางนี้เนื่องจากสามารถเรียนรู้จากข้อเสนอแนะของนักเรียนได้อย่างรวดเร็ว และนำไปสู่การปรับปรุงประสบการณ์การใช้งานให้ดียิ่งขึ้น เรามีแผนจะฝึกพฤติกรรมดังกล่าวโดยตรงในโมเดลหลักของเรา หลังจากลองไปเรื่อยๆ และได้ฟีดแบ็กจากผู้เรียนว่าตรงไหนเวิร์กที่สุด 

เรายังสำรวจฟังก์ชันการทำงานเพื่อทำให้โหมดการเรียนรู้มีความน่าสนใจและเป็นประโยชน์มากขึ้นสำหรับผู้เรียน เช่น:

  • การสร้างภาพที่ชัดเจนยิ่งขึ้นเพื่ออธิบายแนวคิดที่ซับซ้อนหรือเนื้อหาที่มีข้อความเยอะ
  • กำหนดเป้าหมายและการติดตามความคืบหน้าตลอดทุกบทสนทนา
  • ออกแบบการเรียนรู้เฉพาะบุคคลให้ตรงกับระดับความสามารถและเป้าหมายของผู้เรียนแต่ละคนอย่างละเอียด

งานวิจัยด้านการใช้ AI สำหรับการศึกษายังอยู่ในช่วงพัฒนา เพื่อหาแนวทางที่เหมาะสมที่สุดในการใช้ AI ในการเรียนการสอน OpenAI กำลังสนับสนุนการวิจัยเกี่ยวกับการเรียนรู้และ AI ร่วมกับพันธมิตรหลายรายในโครงการ NextGenAI และทำงานร่วมกับผู้เชี่ยวชาญจากโครงการ SCALE Initiative จาก ศูนย์เร่งรัดการเรียนรู้ของมหาวิทยาลัยสแตนฟอร์ด(เปิดในหน้าต่างใหม่) เพื่อศึกษาและแบ่งปันว่า การใช้เครื่องมือ AI มีผลต่อผลลัพธ์การเรียนรู้ในระดับการศึกษาอย่าง K-12 อย่างไร

เรากำลังทำการศึกษาระยะยาวเพื่อดูว่าผู้เรียนเรียนกับ AI ได้ดีที่สุดโดยใช้วิธีไหน แล้วจะเอาผลที่ได้มาเขียนวิเคราะห์เจาะลึก ว่าการออกแบบโมเดลมีความสัมพันธ์กับการรับรู้อย่างไร พร้อมเอามาปรับปรุงผลิตภัณฑ์ในอนาคต นอกจากนี้เรายังทำงานร่วมกับวงการการศึกษาเพื่อพัฒนา AI ให้ช่วยสร้างประโยชน์ให้แก่ผู้เรียนทั่วโลกได้จริง