Salta al contingut principal
OpenAI

29 de juliol del 2025

Producte

Presentem el mode d'estudi

Una nova manera d'aprendre a ChatGPT que ofereix orientació pas a pas en lloc de respostes ràpides.

S'està carregant…

Avui presentem el mode d'estudi a ChatGPT, una experiència d'aprenentatge que t'ajuda a resoldre problemes pas a pas en lloc de limitar-se a donar una resposta. Des d'avui, està disponible per als usuaris amb sessió iniciada als plans Free, Plus, Pro i Team, i arribarà a ChatGPT Edu en les properes setmanes.

ChatGPT s'està convertint en una de les eines d'aprenentatge més utilitzades del món. Els estudiants hi recorren per resoldre deures difícils, preparar exàmens i explorar nous conceptes. Però el seu ús en educació també ha plantejat una pregunta important: com ens assegurem que s'utilitza per donar suport a un aprenentatge real i no només per oferir solucions sense ajudar els estudiants a entendre-les?

Hem creat el mode d'estudi per ajudar a respondre aquesta pregunta. Quan els estudiants l'utilitzen, es troben amb preguntes orientatives que adapten les respostes al seu objectiu i nivell per ajudar-los a construir una comprensió més profunda. El mode d'estudi està dissenyat per ser atractiu i interactiu, i per ajudar els estudiants a aprendre alguna cosa, no només a acabar alguna cosa.

Com s'ha creat el mode d'estudi

A nivell intern, el mode d'estudi funciona amb instruccions de sistema personalitzades que hem escrit en col·laboració amb professors, científics i experts en pedagogia per reflectir un conjunt bàsic de comportaments que afavoreixen un aprenentatge més profund, com ara: fomentar la participació activa, gestionar la càrrega cognitiva, desenvolupar de manera proactiva la metacognició i l'autoreflexió, fomentar la curiositat i oferir comentaris útils i de suport. Aquests comportaments es basen en una llarga trajectòria de recerca en ciències de l'aprenentatge i defineixen com respon el mode d'estudi als estudiants.

«En lloc de fer la feina per ells, el mode d'estudi anima els estudiants a pensar de manera crítica sobre el seu aprenentatge. Funcions com aquestes són un pas positiu cap a un ús eficaç de la IA per aprendre. Fins i tot en l'era de la IA, el millor aprenentatge continua produint-se quan els estudiants se senten motivats i participen activament amb el material de la lliçó.» —Robbie Torney, Senior Director of AI Programs a Common Sense Media.

Característiques clau

Indicacions interactives: Combina preguntes socràtiques, pistes i indicacions d'autoreflexió per guiar la comprensió i promoure l'aprenentatge actiu, en lloc de proporcionar respostes directament.

Respostes estructurades: La informació s'organitza en seccions fàcils de seguir que destaquen les connexions clau entre temes, mantenen l'interès amb la quantitat justa de context i redueixen la sensació de saturació en temes complexos.

Suport personalitzat: Les lliçons s'adapten al nivell adequat per a l'usuari, a partir de preguntes que avaluen el nivell d'habilitat i la memòria de xats anteriors.

Comprovacions de coneixement: Els qüestionaris i les preguntes obertes, juntament amb comentaris personalitzats per fer un seguiment del progrés, afavoreixen la retenció del coneixement i la capacitat d'aplicar-lo en contextos nous.

Flexibilitat: Activa i desactiva fàcilment el mode d'estudi durant una conversa, amb la flexibilitat d'adaptar-te als teus objectius d'aprenentatge en cada conversa.

Com fan servir els estudiants el mode d'estudi

El mode d'estudi s'ha creat pensant en estudiants universitaris. Alguns comentaris que vam sentir dels estudiants durant les primeres proves:

«La millor manera de descriure-ho és com unes “hores de tutoria” en directe, 24/7 i que ho saben tot.» —Noah Campbell, estudiant universitari

«El mode d'estudi va fer una gran feina desglossant material dens en explicacions clares i ben pautades.» —Caleb Masi, estudiant universitari

«Vaig posar el mode d'estudi a prova perquè em fes de tutor en un concepte que havia intentat aprendre moltes vegades abans: les codificacions posicionals sinusoidals. Era com un tutor que no es cansa de les meves preguntes. Després d'una sessió de treball de 3 hores, finalment ho vaig entendre prou bé per sentir-me segur.» —Maggie Wang, estudiant universitària

Maneres d'utilitzar el mode d'estudi inspirades en estudiants universitaris del laboratori de 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

Com començar

El mode d'estudi és especialment útil per ajudar amb els deures, preparar exàmens i aprendre temes nous. Per provar-lo, selecciona «Study and learn» a les eines de ChatGPT i fes una pregunta.

Limitacions i què ve després

Aquest és un primer pas en un camí més llarg per millorar l'aprenentatge a ChatGPT. Avui, el mode d'estudi funciona amb instruccions de sistema personalitzades. Hem triat aquest enfocament perquè ens permet aprendre ràpidament a partir dels comentaris reals dels estudiants i millorar l'experiència, encara que això comporti alguns comportaments incoherents i errors entre converses. Tenim previst incorporar aquest comportament directament als nostres models principals un cop hàgim après què funciona millor mitjançant la iteració i els comentaris dels estudiants.

També estem explorant funcionalitats per fer que el mode d'estudi sigui més atractiu i útil per als estudiants, com ara:

  • Visualitzacions més clares per a conceptes complexos o amb molta càrrega de text
  • Definició d'objectius i seguiment del progrés entre converses
  • Una personalització més profunda adaptada al nivell i als objectius de cada estudiant

El panorama de recerca encara s'està definint quant a les millors maneres d'aplicar la IA a l'educació. OpenAI impulsa més recerca sobre aprenentatge i IA a través de diversos socis de la seva iniciativa NextGenAI, i col·labora amb experts de la SCALE Initiative de l'Accelerator for Learning de la Stanford University(s'obre en una finestra nova) per estudiar i compartir com les eines d'IA influeixen en els resultats d'aprenentatge en àmbits com l'educació K-12.

Mentre duem a terme estudis a més llarg termini sobre com aprenen millor els estudiants amb la IA, tenim la intenció de publicar una anàlisi més profunda del que hem après sobre els vincles entre el disseny del model i la cognició, donar forma a futures experiències de producte a partir d'aquests coneixements i treballar colze a colze amb l'ecosistema educatiu en general per garantir que la IA beneficiï els aprenents de tot el món.