Pasar al contenido principal
OpenAI

2 de febrero de 2025

Lanzamiento

Presentamos la investigación a fondo

Un agente que aplica el razonamiento para sintetizar grandes cantidades de información en línea y llevar a cabo tareas de investigación de varios pasos por ti. Disponible actualmente para los usuarios Pro y próximamente para los usuarios Plus y Team.

Cargando...

Actualización del 10 de febrero de 2026: Ahora puedes conectar la investigación profunda a cualquier MCP o aplicación y restringir las búsquedas en la web a sitios de confianza, para que puedas enfocarte en fuentes autenticadas y estándares de la industria. También puedes seguir el progreso en tiempo real e interrumpir para perfeccionar con prompts de seguimiento o nuevas fuentes. Hemos actualizado la experiencia visual para que sea más fácil iniciar, seguir y revisar tu investigación de principio a fin.


Actualización del 17 de julio de 2025: La investigación profunda ahora puede ser aún más profunda y amplia con acceso a un navegador visual como parte del agente de ChatGPT. Para acceder a estas capacidades actualizadas, simplemente selecciona “modo agente” en el menú desplegable del compositor e ingresa tu consulta directamente. La funcionalidad original de investigación profunda sigue disponible a través de la opción “investigación profunda” en el menú de herramientas.


Actualización del 24 de abril de 2025: Estamos aumentando significativamente la frecuencia con la que puedes usar la investigación profunda: los usuarios Plus, Team, Enterprise y Edu ahora tienen 25 consultas al mes, los usuarios Pro tienen 250 y los usuarios Free tienen 5. Esto es posible gracias a una nueva versión ligera de la investigación profunda, impulsada por una versión de o4-mini, diseñada para ser más rentable sin comprometer la alta calidad. Una vez que alcances tu límite de la versión completa, tus consultas cambiarán automáticamente a la versión ligera.


Actualización del 25 de febrero de 2025: Todos los usuarios Plus ahora pueden usar investigación profunda.


Actualización del 5 de febrero de 2025: La investigación profunda ya está disponible para los usuarios Pro en el Reino Unido, Suiza y el Área Económica Europea.


Con la investigación a fondo en ChatGPT, la nueva herramienta que realiza búsquedas de varios pasos en Internet, podrás solucionar tareas complejas. Es capaz de lograr en 20 o 30 minutos lo que a un ser humano le llevaría muchas horas.

La investigación a fondo es el nuevo agente de OpenAI que puede trabajar por ti de forma independiente: tú le envías un mensaje solicitando lo que necesitas y ChatGPT se encargará de buscar, analizar y sintetizar cientos de fuentes en línea para crear un informe detallado digno de un analista de investigación. Esta nueva herramienta está impulsada por una versión del nuevo modelo OpenAI o3, optimizada para navegar por la web y analizar datos, que aprovecha el razonamiento para buscar, interpretar y analizar grandes cantidades de texto, imágenes y archivos PDF publicados en Internet, reaccionando a la información que encuentra en función de tus necesidades.

Para poder crear nuevos conocimientos es necesario poder sintetizarlos. Por eso, la investigación a fondo es un avance esencial hacia el gran objetivo de desarrollar la AGI, que desde hace ya mucho tiempo consideramos capaz de generar nuevas investigaciones científicas.

Por qué creamos la investigación a fondo

La investigación a fondo está pensada para personas que realizan un trabajo intensivo de conocimiento en campos como las finanzas, la ciencia, la política y la ingeniería y necesitan una investigación minuciosa, precisa y digna de confianza. También puede resultarles muy útil a los compradores exigentes que buscan recomendaciones totalmente personalizadas para hacer compras que normalmente obligan a realizar una investigación minuciosa, como sucede con los automóviles, los electrodomésticos y los muebles. Cada salida está ampliamente documentada, pues incluye citas claras y una síntesis de su pensamiento, con lo que facilita la consulta de las referencias y la verificación de la información. Esta herramienta es especialmente eficaz para encontrar información especializada y que no sea intuitiva, ya que para encontrarla habría que navegar por numerosos sitios web. La investigación a fondo te permite ganar una cantidad de tiempo nada despreciable, ya que con una sola consulta puedes descargar y agilizar búsquedas web complejas que, de otro modo, te tomarían mucho tiempo.

La investigación a fondo se encarga de descubrir, analizar y consolidar información obtenida en la web de forma independiente. Para lograrlo, se la entrenó en tareas del mundo real que requieren el uso de navegadores y herramientas Python, aplicando los mismos métodos de aprendizaje por refuerzo que hay detrás de OpenAI o1, nuestro primer modelo de razonamiento. Si bien o1 muestra unas capacidades asombrosas para la codificación, las matemáticas y otras disciplinas técnicas, para muchos de los desafíos del mundo real es necesario contar con un contexto amplio y recopilar información de diferentes fuentes en línea. Para salvar esa diferencia, la investigación a fondo recurre a estas capacidades de razonamiento, que le permiten abordar los tipos de problemas a los que las personas nos enfrentamos en el trabajo y en el día a día.

Cómo usar la investigación a fondo

En ChatGPT, selecciona “Investigación a fondo” en el editor de mensajes e ingresa tu consulta. Dile a ChatGPT lo que necesitas, por ejemplo, un análisis de la competencia entre plataformas de streaming o un informe personalizado sobre la mejor bicicleta para ir al trabajo. Si deseas añadirle más contexto a tu pregunta, puedes adjuntar archivos u hojas de cálculo. Una vez que comienza a ejecutar la búsqueda, aparece una barra lateral con un resumen de los pasos que ha ido siguiendo y las fuentes que consulta.

La investigación a fondo puede tomar de 5 a 30 minutos para completar su trabajo, ya que dedica el tiempo necesario a adentrarse en las profundidades de la web. Mientras tanto, puedes ausentarte o trabajar en otras tareas, pues te enviará una notificación una vez finalice la investigación. Los datos de salida finales se presentan en el chat a modo de informes. A estos informes, en las próximas semanas les añadiremos imágenes incrustadas, visualizaciones de datos y otros resultados analíticos que les aportarán mayor claridad y contexto.

Comparado con la investigación a fondo, GPT‑4o es ideal para conversaciones en tiempo real que incluyan, por ejemplo, texto, voz, imágenes y videos. Cuando se trata de consultas multifacéticas y centradas en un ámbito en particular, en el que la minuciosidad y el detalle sean esenciales, la capacidad de la investigación a fondo para realizar exploraciones exhaustivas y citar cada argumento marca la diferencia entre un resumen rápido y una respuesta verificada y bien documentada que se puede utilizar como producto de trabajo.

GPT-4o

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

Compiling comprehensive data on iOS and Android adoption rates, the percentage of populations interested in learning another language, and changes in mobile penetration over the past decade for the top 10 developed and developing countries by GDP is challenging due to data limitations. However, based on available information, we can provide insights and recommendations for targeting markets with a new iOS translation app powered by ChatGPT.

Top 10 Developed Countries by GDP:

  1. United States
  2. Japan
  3. Germany
  4. United Kingdom
  5. France
  6. Italy
  7. Canada
  8. South Korea
  9. Australia
  10. Spain

Top 10 Developing Countries by GDP:

  1. China
  2. India
  3. Brazil
  4. Russia
  5. Indonesia
  6. Mexico
  7. Turkey
  8. Saudi Arabia
  9. Argentina
  10. South Africa

Insights:

  • iOS and Android Adoption Rates: Globally, Android holds a dominant market share of approximately 70.93%, while iOS accounts for about 28.32% as of 2024. In the United States, iOS leads with a 58.81% market share. Other developed countries like Japan, Canada, Australia, and the United Kingdom also show a higher preference for iOS devices. In contrast, developing countries such as India and Brazil have a higher prevalence of Android devices.
  • Interest in Language Learning: While specific percentages of populations interested in learning another language are not readily available, the global popularity of language learning apps like Duolingo, which had approximately 14.3 million downloads in July 2024, indicates a significant interest. This interest is likely higher in countries with diverse linguistic landscapes or where English is not the primary language.
  • Mobile Penetration Over the Past Decade: Mobile phone ownership has seen substantial growth globally. In the United States, smartphone ownership increased from 35% in 2011 to 91% in 2024. Developing countries have also experienced significant growth in mobile penetration, contributing to increased access to digital services.

Recommendations:

Considering the available data and focusing on markets where ChatGPT is currently active, the following developed countries are promising targets for a new iOS translation app:

  • United States: High iOS market share and significant interest in language learning.
  • United Kingdom: Substantial iOS user base and a multicultural population with diverse language needs.
  • Canada: Notable iOS adoption and a bilingual population (English and French), increasing the demand for translation services.

Among developing countries, the following are noteworthy:

  • China: Despite Android's dominance, the large population and growing interest in English and other languages present a significant opportunity.
  • India: High Android usage, but a growing middle class with increasing iOS adoption and a strong interest in language learning, especially English.
  • Brazil: Predominantly Android users, but with a sizable market for language learning apps, particularly for English and Spanish.

Focusing on these markets aligns with ChatGPT's current availability and leverages existing mobile adoption trends and language learning interests.

Investigación a fondo

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

Top 10 Developed Economies (by GDP)Smartphone OS Share, Language-Learning Interest, and Mobile Penetration Growth

Country

iOS Market Share

Android Market Share

Interest in New Language

(% of population)

Mobile Penetration Change (2013→2023)

United States

(USA)

~58% iOS vs 42% Android

(see left)

High:

70% regret losing foreign-language ability (indicating strong desire to improve)

56%→82%

smartphone penetration (↑26 pp)

Japan

~69% iOS vs 31% Android

(see left)

High:

Over 50% want to learn English

~30%→79%

(approx.) (↑~50 pp)

Germany

~39% iOS vs 60% Android

(see left)

High:

86% of Europeans say everyone should speak ≥1 foreign language (strong pro-language attitude)

40%→82%

(↑42 pp)

United Kingdom

(UK)

~52% iOS vs 47% Android

(see left)

Moderate-High:

~73% have some interest (only 27% “no interest” in new languages)

62%→82%

(↑20 pp)

France

~35% iOS vs 64% Android

(see left)

High:

86% (EU average) favor multilingualism; English widely seen as important

42%→83%

(↑40 pp)

Italy

~30% iOS vs 69% Android

(see left)

High:

86% (EU avg.) favor language learning; 1 in 4 regret not learning another

41%→85%

(↑44 pp)

Canada

~60% iOS vs 40% Android

(see left)

Moderate:

Many bilingual (English/French); rising interest in third languages (no recent % data)

56%→~80%

(↑ ~24 pp) (est., similar to US)

South Korea

~24% iOS vs 76% Android

(see left)

Moderate:

Strong English education focus; ~40% of teens are learning English

73%→~95%

(↑ ~22 pp) – already very high by 2013 (near saturation now)

Australia

~55% iOS vs 45% Android

(see left)

Moderate:

~70% see learning languages as valuable (English dominant but interest in Asian languages growing)

65%→~85%

(↑ ~20 pp) (est., high smartphone use)

Spain

~20% iOS vs 79% Android

(see left)

High:

88% of Spaniards learned a foreign language in school (e.g. English); strong cultural interest

55%→~85%

(↑ ~30 pp) (est., nearing Western Europe peers)

Top 10 Developing/Emerging Economies (by GDP)(ChatGPT availability considered)

Country

iOS Market Share

Android Market Share

Interest in New Language

(notable stats)

Mobile Penetration Change (2013→2023)

China

^(ChatGPT restricted)

~24% iOS vs 75% Android

(see left)

Very High:

Hundreds of millions learning English (but ChatGPT not officially accessible)

47%→68%

(↑21 pp)

India

~4% iOS vs 95% Android

(see left)

High:

English compulsory in many schools; strong economic motivation (80% link English to higher income)

~5%→46%

(↑ ~41 pp) (huge jump in smartphone adoption)

Brazil

~18% iOS vs 82% Android

(see left)

High:

Great demand for English – only ~5% speak it, but most see it as key skill

26%→67%

(↑40 pp)

Russia

^(ChatGPT limited)

~30% iOS vs 69% Android

(see left)

Moderate:

English learning common (compulsory in school); interest exists but ChatGPT availability is uncertain

36%→74%

(↑38 pp)

Mexico

~24% iOS vs 76% Android

(see left)

High:

Strong desire to learn English for US job/migration; ~50% of students study English in school (est.)

37%→62%

(↑25 pp)

Indonesia

~12% iOS vs 88% Android

(see left)

High:

English seen as gateway skill; government programs to improve English proficiency

<30%→68%

(↑ ~40 pp)

Turkey

~15% iOS vs 85% Android (est.)

(see left)

High:

English highly valued (universal in education);

80%

link English to better jobs

30%→75%

(↑45 pp)

Saudi Arabia

~24% iOS vs 76% Android

(see left)

Moderate:

English widely taught; 92% smartphone ownership (many already bilingual in English/Arabic)

73%→~95%

(↑ ~22 pp) (early adopter; near saturation now)

South Africa

~16% iOS vs 83% Android

(see left)

High:

Multilingual society; English and Afrikaans taught alongside native languages – cultural impetus to learn others

40%→~60%

(↑ ~20 pp) (est., steady growth)

Argentina

~12% iOS vs 88% Android

(see left)

High:

Strong interest in English (Argentina leads Latin America in English proficiency)

31%→~70%

(↑ ~39 pp) (est., sharp rise with smartphone adoption)

Sources: Smartphone OS shares are from StatCounter/Statista data (2023–24). Language-interest metrics come from surveys by Preply, Eurobarometer, Babbel, etc. (e.g. UK 73% interest; US 70% regret lack of languages; Japan >50% want English; Pearson global survey). Mobile penetration is measured as smartphone ownership percentage – dramatic growth is noted in developing markets (e.g. Brazil +40 points) and high saturation in developed ones (e.g. UK ~82%) over the last decade.


Recommendations: Based on the above, prime targets for a new ChatGPT‑powered iOS translation app would be countries with large iOS user bases and strong language-learning demand, where ChatGPT is accessible. Notably, Japan, the U.S., UK, Canada, and Australia emerge as top choices. These markets pair high iOS adoption (50–60%+ share) with significant enthusiasm for language learning – for example, Japan’s iPhone dominance and widespread desire to learn English make it ideal. English-speaking countries like the US, UK, Canada, and Australia, despite being monolingual societies, show substantial interest in learning other languages (e.g. Spanish or French), and all have over 80% smartphone penetration and millions of iPhone users.

Among emerging economies, Mexico and Brazil stand out as secondary targets: although Android prevails, their sheer population sizes mean tens of millions of iPhone users exist, and interest in English is very high for career and education reasons. These Latin American markets (where ChatGPT is active) could yield strong adoption for an iOS-only app, especially given the motivation to learn English. Conversely, China and Russia are less feasible – China’s OS split skews Android and ChatGPT is not officially available there, and Russia faces access and regulatory uncertainties.

In summary, focus on iOS-heavy, pro-learning markets: Japan and Western countries (US, UK, Canada, Australia, plus high-income Europe like Germany and France to a lesser degree) should be the first-tier targets. They combine robust iOS usage with favorable language-learning attitudes. A second tier includes large-population developing markets (Mexico, Brazil, perhaps Saudi Arabia for its historically high iPhone uptake) where interest in English is strong – these can be approached once the app gains traction in the primary markets. Such a strategy ensures the app launches where it has the greatest alignment of platform (iOS) presence and user demand for translation/language tools, maximizing the likelihood of adoption and growth.

La investigación a fondo responde a los mensajes con todo detalle y ofrece datos desglosados por países, tanto de los 10 principales países desarrollados como de los 10 principales países en desarrollo, para que la consulta y la comparación resulten más sencillas. A partir de esa información, puede ofrecer recomendaciones detalladas para entrar en cada mercado, fundamentadas y útiles.

¿Cómo funciona?

La investigación a fondo se entrenó aplicando el aprendizaje por refuerzo de extremo a extremo a tareas difíciles de navegación y razonamiento en una amplia gama de dominios. Este entrenamiento le permitió aprender a planificar y ejecutar una trayectoria de varios pasos hasta encontrar los datos que necesita, retrocediendo y reaccionando a la información en tiempo real siempre que sea necesario. El modelo también tiene la capacidad de explorar los archivos que cargan los usuarios, elaborarlos, refinarlos y mejorarlos, generar gráficos e incrustarlos en sus respuestas valiéndose de la herramienta Python, así como citar frases o pasajes concretos de sus fuentes. Gracias a este entrenamiento, llega a nuevos máximos en una serie de evaluaciones públicas centradas en problemas del mundo real.

El último examen de la humanidad

En la prueba Humanity’s Last Exam(se abre en una nueva ventana), un estudio publicado recientemente que pone a prueba la inteligencia artificial en una amplia gama de temas con preguntas de nivel experto, el modelo que impulsa la investigación profunda alcanza un nuevo récord con un 26,6 % de precisión. Esta evaluación consta de más de 3000 preguntas con respuestas de opción múltiple y cortas acerca de más de 100 temas, que van desde la lingüística a los cohetes espaciales, pasando por las obras clásicas o la ecología. Si se compara con OpenAI o1, los mayores avances se registraron en química, ciencias humanas y sociales y matemáticas. El modelo que hace posible la investigación a fondo presentó un enfoque similar al humano al buscar eficazmente información especializada cada vez que era necesario.

ModeloPrecisión (%)
GPT-4o3.3
Grok-23.8
Claude 3.5 Sonnet4.3
Gemini Thinking6.2
OpenAI o19.1
DeepSeek-R1*9.4
OpenAI o3-mini (medio)*10.5
OpenAI o3-mini (alto)*13.0
Deep Research de OpenAI**26.6
* El modelo no es multimodal; se evalúa en un subconjunto de solo texto.
** con herramientas de navegación + Python

GAIA

En la prueba GAIA(se abre en una nueva ventana)1, un estudio de referencia público que evalúa la IA con preguntas del mundo real, el modelo que hace posible la investigación a fondo alcanza un nuevo nivel de excelencia (SOTA, por sus siglas en inglés y encabeza la clasificación(se abre en una nueva ventana) externa. Para llevar a cabo estas tareas con éxito, que comprenden preguntas de tres niveles de dificultad, se necesitan capacidades como el razonamiento, la fluidez multimodal, la navegación por Internet y la destreza en el uso de herramientas.

GAIA
Nivel 1Nivel 2Nivel 3Promedio
SOTA anterior(se abre en una nueva ventana)67.9267.4442.3163.64
Deep Research (pass@1)74.2969.0647.667.36
Deep Research (cons@64)78.6673.2158.0372.57

Ejemplos de tareas para la prueba GAIA

In Nature journal's Scientific Reports conference proceedings from 2012, in the article that did not mention plasmons or plasmonics, what nano-compound is studied? Don't use the prefix nano in your answer if there is one.

[The remaining Chain-of-Thought messages and the final answer are hidden to protect the benchmark's ground truth answer.]

Clarifying the search

I’m piecing together the request for an article from 2012 in Scientific Reports that details a nano-compound, excluding any related to plasmonics. Likely, this involves filtering specific topics or compounds, like silver or graphene.

Piecing together details

I'm sub-searching "Scientific Reports 2012 nanoparticle," likely seeking nano-compounds. Interested in filtering out plasmon-related topics, possibly focusing on silver, graphene, or quantum dots.

[acción de búsqueda]

Navegando por los filtros de búsqueda

I’m digging into advanced search filters on nature.com and Scientific Reports for 2012, trying to pinpoint articles on amorphous carbon nanoparticles in food caramels.

Identifying conference proceedings

The search results reveal a conference proceeding titled "2D quasiperiodic plasmonic crystals" from 2012, likely found under the "Conference Proceedings" category in Scientific Reports.

[acción de explorar]

Reflecting on potential issues

I'm considering the reasons behind a web page misconception, likely due to an outdated agent type or inadvertent blockage.

[acción de explorar]

Considering dynamic options

I'm thinking about a nature site with dynamic content or a cached version. Alternatively, trying a search for specific phrases might help.

[acción de búsqueda]

Pinpointing key features

OK, I'm identifying four conference proceedings from 2012 in Sci Rep. Notably, some mention "plasmonic" and should be excluded.

[acción de explorar]

Piecing together insights

I’m gathering info on accessing cached versions or snippet expansions for specific titles to ensure comprehensive analysis.

[acción de búsqueda]

Pulling together the details

I’m noting the progression from the 2012 European Materials Research Society Spring Meeting to the scientific report, focusing on conference proceedings. This approach helps establish context and relevance.

[acción de búsqueda]

Tracking journal clues

Trying to connect conference proceedings from late 2012 with "Scientific Reports" journal, focusing on plasmonic 2D quasiperiodic materials. This approach feels methodical and precise.

[acción de búsqueda]

Analyzing event details

Noting that the search results [8] include a page likely summarizing the European Materials Research Society 2012 Spring Meeting, including 25 symposia.

[acción de explorar]

Piecing together research

I’m examining a likely collection page with 4 articles, considering plasmonic and metamaterial topics, and identifying key references from the European Materials Research Society 2012 Spring Meeting.

[acción de explorar]

Pinpointing the focus

I’m focusing on the 2012 conference proceedings in "Scientific Reports" from E-MRS, likely involving topics like "2D quasiperiodic plasmonic crystals" and "Layered plasmonic cloaks to tailor the optical scattering at the nanoscale."

[acción de explorar]

Evaluating library sources

Thinking about special issue E-MRS 2012 Sci rep invited paper Monticone and metamaterials lab at News Archives – 2012.

[acción de explorar]

Assessing accessibility

I'm gathering info on potential site access issues, considering outdated status or blockages. Also, evaluating the Monticone site for a list reference.

[acción de explorar]

Piecing together E-MRS 2012

I'm trying to link "Layered Plasmonic Cloaks" to E-MRS 2012. Considering other possible topics like graphene and catalysis.

[acción de explorar]

Identifying relevant topics

I’m gathering info on topics like graphene, photovoltaics, and nanostructured compounds, while excluding plasmonic-related ones. This leads me to focus on nanotechnology aspects more broadly.

[acción de explorar]

Adjusting my focus

I’m broadening the search parameters by entering specific site and scholar identifiers to pinpoint articles about 2D quasiperiodic plasmonic crystals in Nature Scientific Reports from 2012.

[acción de búsqueda]

Identifying non-plasmonic possibilities

I'm narrowing down the search to identify articles from the 2012 E-MRS special issue in Scientific Reports. This involves checking titles for non-plasmonic topics, like graphene or functional oxides. Progress is evident through focused searches and exclusion of plasmonic articles.

[acción de búsqueda]

Piecing together clues

I'm analyzing interactions in a graphene superlattice, likely from a Sci Rep article. Considering titles by authors like Padooru, Yakovlev, Chen, and Alu.

[acción de búsqueda]

Piecing together the puzzle

I’m gathering info on E-MRS 2012 Spring Meeting's Sci Rep proceedings, focusing on invited papers, without plasmonic phenomena. Types under review are graphene, catalysis, energy materials, nanomedicine, and sensors.

[acción de búsqueda]

Tareas a nivel experto

En una evaluación interna de tareas a nivel experto en una serie de dominios, los expertos en cada uno de ellos consideraron que la investigación a fondo había permitido automatizar muchas horas de ardua investigación manual. 

Tasa de aprobación frente a cantidad máxima de solicitudes a herramientas
Tasa de aprobaciónCantidad máxima de solicitudes a herramientas
Cuanto más navega y reflexiona el modelo sobre lo que está explorando, mejor rendimiento tiene; por eso, es importante darle tiempo para pensar.
Ejemplos de tareas a nivel experto
Tiempo ahorrado en la tarea: 4 horas

I am a researcher interested in bringing mixed-gas sorption capabilities to my lab. Please discuss the differences between pure- and mixed-gas sorption for glassy polymers, how the dual-mode sorption model can be used to predict mixed-gas sorption behavior in glassy polymers (include equations where applicable), and what challenges there are in accurately predicting pure- and mixed-gas sorption using the dual-mode sorption model. Only include open-source information as of October 1, 2024.

Pure vs. mixed-gas sorption in glassy polymers: In a glassy polymer (below TgT_g), a single gas typically exhibits a concave sorption isotherm: uptake rises sublinearly with pressure, unlike the linear Henry’s-law behavior above TgT_g. This is attributed to “dual-mode” sorption: some penetrant dissolves in the dense polymer matrix (obeying Henry’s law) while additional penetrant saturates specific microvoid “sites” (a Langmuir-type adsorption in the polymer’s nonequilibrium free volume). By contrast, when two or more gases are present, they compete for those limited Langmuir sorption sites. As a result, each component’s sorbed concentration in a mixture is generally lower than it would be at the same partial pressure alone. In particular the less soluble (lower-affinity) gas tends to be more strongly suppressed, often causing the mixed-gas solubility selectivity (ratio of concentrations) to exceed the ideal value predicted from pure-gas isotherms. For example, in CO₂/CH₄ mixtures both components sorb less than in their pure-gas cases (especially CH₄), so the CO₂/CH₄ sorption selectivity is higher under mixture conditions. In extreme cases, mixed-gas effects can even reverse performance trends observed with single gases. (We note that unlike competitive sorption, synergistic sorption – where one gas increases the sorption of another via polymer swelling – is usually minor in rigid high-free-volume polymers under moderate pressures.)

Dual-mode sorption model and mixed-gas prediction: The dual-mode sorption (DMS) model quantitatively captures glassy polymer sorption by superposing a Henry’s-law term and a Langmuir term. For a single gas, the sorbed concentration CC (e.g. in cm³(STP) gas per cm³ polymer) is written as:

C(p)=kDp  +  CHbp1+bp.C(p) = k_D\,p \;+\; \frac{C'_H\,b\,p}{\,1 + b\,p\,}\,.

Here kDk_D is the Henry’s law coefficient for dissolution, CHC'_H is the Langmuir capacity constant (proportional to the polymer’s unrelaxed free-volume or “hole” capacity), and bb is the Langmuir affinity constant. This empirical formula yields the characteristic concave isotherm of glassy polymers and reduces to simple Henry’s law at the glass-transition (since CH0C'_H \to 0 as TTgT \to T_g). The same three parameters (kD,CH,bk_D, C'_H, b) are obtained by fitting pure-gas sorption data and are then used to predict mixture sorption. For a binary mixture of gases A and B (with partial pressures pA,pBp_A, p_B), the DMS model assumes each gas obeys its own Henry’s term and that both compete for the same Langmuir sites. One convenient form is to write the total sorbed concentration as the sum of contributions from each gas:

Ctot=kD,ApA+kD,BpB  +  CH,AbApA  +  CH,BbBpB1+bApA+bBpB,C_{\text{tot}} = k_{D,A}p_A + k_{D,B}p_B \;+\; \frac{\,C'_{H,A}\,b_A\,p_A \;+\; C'_{H,B}\,b_B\,p_B\,}{\,1 + b_A p_A + b_B p_B\,}\,,

which implicitly means the concentration of component i in the mixture is Ci=kD,ipi+CH,ibipi1+jbjpjC_i = k_{D,i} p_i + \frac{C'_{H,i} b_i p_i}{\,1+\sum_j b_j p_j\,}. This reduces to the single-gas formula when the other component’s pressure is zero. In practice, partial pressure in these equations is often replaced by fugacity for accuracy at high pressures, though using fugacities or pressures gives nearly the same results if applied consistently. The DMS mixed-gas model predicts the competitive sorption effect observed experimentally – namely, each gas’s uptake is depressed relative to its pure-gas sorption isotherm.

Challenges and limitations: Although the dual-mode model is widely successful in correlating sorption data, it has notable limitations in predicting sorption behavior. First, the DMS model is empirical – its fitted parameters are not universal constants but can vary with polymer formation history, physical aging, and temperature/pressure range. This means a parameter set obtained under one set of conditions may lack predictive power outside its calibration range. For instance, sorption isotherms measured only over a limited pressure range can be fit well by DMS, but extrapolating beyond that (especially approaching plasticization pressures) may be unreliable. Indeed, multiple distinct combinations of kDk_D, CHC'_H, bb can sometimes fit the same pure-gas isotherm almost equally well – yet they yield markedly different mixed-gas predictions. This sensitivity undermines confidence in mixture forecasts, as one study showed that using different pure-gas fit sets led to only qualitative agreement with some mixed-CO₂/CH₄ data.

Furthermore, DMS inherently assumes a fixed population of Langmuir sites (microvoids) and ignores polymer relaxation or swelling induced by sorbate. In reality, penetrant-induced swelling (plasticization) can increase free volume and sorption capacity, especially for highly condensable gases at high activity – an effect the basic DMS model cannot capture. In binary sorption, this means any synergistic increase in sorption due to a second gas (or due to polymer dilation) is unaccounted for in the standard model. Conversely, the model also cannot describe sorption isotherm shapes that deviate from concave Langmuir-type behavior (e.g. sigmoidal isotherms caused by specific polymer-penetrant interactions or clustering). For example, glassy polymers absorbing polar molecules like alcohols can show sigmoidal sorption isotherms, which the simple dual-mode framework fails to represent. Finally, accurately measuring mixed-gas sorption itself is challenging, and discrepancies between idealized model assumptions (e.g. truly zero downstream pressure, no competitive diffusion limitations) and experimental realities can add to prediction error. Despite these challenges, the dual-mode sorption model – with appropriate care – remains a valuable first approximation for interpreting sorption in glassy polymers, and it highlights the key role of competitive site occupancy in mixed-gas environments. Researchers often turn to more elaborate models (e.g. non-equilibrium lattice fluid or thermodynamic theories) when the dual-mode model’s assumptions break down, but such models come at the cost of additional parameters or complexity. In summary, dual-mode sorption provides a useful baseline for pure- and mixed-gas sorption in glassy polymers, but one must be mindful of its empirical nature and the above limitations when predicting multicomponent sorption behavior in practice.

Sources: Dual-mode sorption model and mixed-gas extension; competitive sorption effects in mixtures; model equations and parameters; limitations of DMS model; parameter sensitivity and predictivity issues.

Understanding sorption models

I’m gathering info on pure and mixed-gas sorption in glassy polymers, focusing on the dual-mode sorption model and addressing challenges in modeling predictions.

[acción de búsqueda]

Assessing open access

OK, let me see. The result from MDPI on mixed-gas sorption in glassy polymers is probably open access.

[acción de explorar]

[acción de explorar]

Examining sections
I’m pulling together insights from the Dual Mode Sorption Model and its extended analysis within the MDPI paper.

[acción de explorar]

Clarifying key properties

I’m examining the lab report to understand Henry's law constant, Langmuir affinity constant, and Langmuir capacity constant, which describe gas sorption.

[acción de explorar]

Piecing together

I'm working through the possibility that "Equation (3)" and "Equation (4)" might be images or formula displays and considering consulting the PDF or searching for earlier references to understand them better.

[acción de explorar]

Confirming title relevance

I’m verifying if the document from Freeman and Koros (1980) specifically matches the reference "Model for sorption of mixed gases in glassy polymers" by checking its abstract and title.

[acción de búsqueda]

Examining article connections

I noticed that the result from "pmc.ncbi.nlm.nih.gov" is likely the same MDPI article, and I'm curious to see if it presents the text or a simplified version.

[acción de explorar]

[acción de explorar]

[acción de explorar]

Gathering info

I'm gathering information about pure and mixed gas sorption in glassy polymers. This is a critical step in understanding the material's behavior under different gas environments.

[acción de búsqueda]

Comparing gas sorption

I noticed that carbon dioxide's presence in a mixture affects methane sorption in polymer, reducing methane's sorption compared to a pure gas scenario.

[acción de explorar]

Linking concepts

I’m thinking through how the term "extended dual mode equation mixture" might relate to dual mode superconducting cable equations. This shows potential for connecting concepts across fields.

[acción de búsqueda]

Requesting review details

I'm noting the request to review "Theories of Sorption and Transport in Polymer Membrane."

[acción de explorar]

Checking PDF link

I’m curious about Result [2] and exploring the snippet, which involves extending a dual-mode sorption model to a binary mixture and expressing concentration of A in terms of partial pressures and constants.

[acción de búsqueda]

Predicting sorption behavior

The dual-mode model anticipates that adding a second gas reduces sorption at a constant partial pressure, unlike pure gas scenarios.

[acción de explorar]

Fetching a PDF

I'm gathering info on a nature.com PDF, possibly an older Yampol'ski article, but thinking about alternative sources like the University of Texas at Austin repository for a text snippet.

[acción de explorar]

Evaluating repository options

I’ve discovered that the UT repository result might not display correctly. Searching within it is uncertain. Alternatively, result [3] contains a snippet describing the dual mode mixture sorption model, explaining competitive effects and its adequacy in modeling experimental data.

[acción de búsqueda]

Refining the focus

I'm adjusting my approach to ensure the search targets the right context.

[acción de búsqueda]

Understanding sorption models

I’m detailing the dual-mode sorption model for pure gases: Henry dissolving and Langmuir microvoid filling. For mixed gases, competitive sorption and non-idealities are emphasized.

[acción de búsqueda]

Exploring hero.epa.gov

Thinking through hero.epa.gov's potential abstract or content.

[acción de explorar]

Refining the model

I'm gathering insights on pure and mixed gas sorption, considering factors like competition, plasticization, and parameter stability. Incorporating mixed-gas data for more accurate predictions.

[acción de explorar]

Addressing dual sorption model challenges

Parameter coupling and non-uniqueness impact predictions. Absence of polymer condition changes might lead to oversights.

[acción de explorar]

Quantifying deviation

I’m quantifying nonideal CO2-CH4 solubility in 6FDA-mPDA, showing mixed gas effects on solubility. Competitive sorption isn’t the sole cause of permeability selectivity decline.

[acción de explorar]

Incorporating references

I'm gathering citations, focusing on open-source materials like MDPI 2019 and Vopicka 2014, to support the discussion on differences and challenges in the dual-mode model for gas sorption in polymeric membranes.

[acción de explorar]

Proposing sections

I'm organizing sections on pure vs mixed-gas sorption, exploring the dual-mode sorption model, and detailing challenges like parameter uncertainty and mixed gas prediction.

Organizing content

I’m focusing on the dual-mode sorption model, detailing pure and mixed-gas sorption behaviors, and highlighting key differences and challenges with bullet points and structured sections for clarity.

[acción de búsqueda]

Choosing citations

OK, let me see. I’m leaning on [3], [20], [22], and [21] for their clear insights into dual-mode sorption and gas mixtures.

Mapping out parameters

I’m piecing together parameter names to avoid confusion. Sticking with (k), (C_H'), and (b) for clarity. The equations for pure gas and mixture are detailed and clearly formatted.

Addressing challenges

I'm tackling multi-solution parameter fits, polymer plasticization, and temporal effects. These intricacies make predicting pure and mixed gas sorption tricky.

Piecing together

I’m structuring sections on sorption differences, the dual-mode model for pure gases, its extension to mixed gases, and the associated challenges. This progression seems logical and effective.

Tasa de aprobación en tareas de nivel experto según el valor económico estimado
Tasa de aprobaciónValor económico estimado
Tasa de aprobación en tareas de nivel experto según las horas estimadas
Tasa de aprobaciónHoras estimadas
El valor económico estimado de la tarea está más correlacionado con la tasa de aprobación que con la cantidad de horas que le tomaría a un ser humano completarla; lo que representa una dificultad para los modelos es distinto de lo que las personas consideran que requiere mucho tiempo.

Limitaciones

La investigación a fondo te permite acceder a nuevas capacidades, pero aún está en sus inicios y tiene algunas limitaciones. A veces, puede generar alucinaciones en sus respuestas o hacer inferencias incorrectas, aunque en mucha menor medida que los modelos ChatGPT existentes, según indican las evaluaciones internas. A veces, le puede costar distinguir entre información fidedigna y rumores. De momento, muestra debilidad a la hora de calibrar la confianza y suele no transmitir con precisión lo que le parece incierto. En el momento de su lanzamiento, los informes y las citas podrían contener pequeños errores de formato, mientras que las tareas podrían tardar un poco más en iniciarse. Con el uso y el tiempo, esperamos que todos estos problemas se corrijan rápidamente.

Acceso

Por el momento, la investigación a fondo en ChatGPT consume muchos recursos informáticos. De hecho, cuanto más tiempo le lleve investigar una consulta, más cálculos de inferencia necesitará. Por eso, para comenzar, te proponemos una versión optimizada para usuarios Pro, que puede responder hasta 100 consultas al mes. Luego, el acceso estará disponible para los usuarios Plus y Team y, posteriormente, los usuarios Enterprise. Aún estamos trabajando para facilitarles el acceso a los usuarios del Reino Unido, Suiza y el Espacio Económico Europeo. 

En breve, todos los usuarios de paga disfrutarán de límites de tarifa significativamente más altos cuando lancemos una versión más rápida y rentable de la investigación a fondo, basada en un modelo más pequeño que sin embargo proporcionará resultados de alta calidad. 

Durante las próximas semanas, e incluso meses, nos dedicaremos a mejorar la infraestructura técnica, haremos un estrecho seguimiento de la versión actual y realizaremos pruebas aún más rigurosas. De este modo, cumpliremos con nuestro principio de despliegue iterativo. Si todas las verificaciones de seguridad siguen cumpliendo nuestras normas de lanzamiento, pensamos que podremos poner la investigación a fondo a disposición de los usuarios Plus en aproximadamente un mes.

¿Qué sigue?

La investigación a fondo está disponible desde hoy en la web de ChatGPT y en el plazo de un mes llegará a las aplicaciones para móviles y computadoras de escritorio. Hasta ahora, la investigación a fondo puede acceder a la web abierta y a cualquier archivo que cargues. En el futuro, podrás conectarte a fuentes de datos más especializadas, ya que su acceso a recursos de suscripción o internos permitirá que sus datos de salida sean aún más sólidos y personalizados.

Además, imaginamos que, a largo plazo, podremos combinar las experiencias virtuales dentro de ChatGPT para llevar a cabo investigaciones y ejecuciones asincrónicas del mundo real. Al combinar la investigación a fondo, que es capaz de llevar a cabo una investigación en línea asincrónica, y Operator, que puede realizar acciones en el mundo real, ChatGPT estará en condiciones de hacer realidad las tareas cada vez más sofisticadas que les solicites.


Anexo del 3 de febrero de 2025: Hemos llevado a cabo rigurosas pruebas de seguridad, evaluaciones de preparación y revisiones de gobernanza en la primera versión de o3 en la que se basa la investigación a fondo y la hemos identificado como de riesgo medio(se abre en una nueva ventana). Además, hemos realizado pruebas de seguridad adicionales destinadas a comprender mejor los riesgos adicionales relacionados con la capacidad para explorar la web de la investigación a fondo, y le hemos añadido nuevas medidas de mitigación. Vamos a seguir haciendo pruebas rigurosas, así como un estricto seguimiento de la actual versión limitada. Cuando extendamos el acceso a los usuarios Plus, daremos a conocer nuestros conocimientos en materia de seguridad y protección de la investigación a fondo en una tarjeta del sistema.

Notas al pie

  1. 1

    Constatamos que las respuestas reales de este conjunto de datos se habían filtrado ampliamente en Internet y por ello bloqueamos varios sitios web o URL para garantizar una evaluación justa del modelo.

Autores

OpenAI

Jefes de investigación

Isa Fulford y Zhiqing Sun

Colaboradores fundadores

Alex Tachard Passos, Alexandra Barr, Allison Tam, Charlotte Cole, Hyung Won Chung, Jason Wei, Jon Blackman, Scott Mayer McKinney y Valerie Qi

Contribuidores clave

Investigación

Elaine Ya Le, Eric Mitchell, Eric Wallace, Hyung Won Chung, Ignasi Clavera, Leo Liu, Lorenz Kuhn, Louis Feuvrier, Max Schwarzer, Saachi Jain, Scottie Yan, Shunyu Yao y Vitchyr Pong.

Implementación

Carpus Chang, Harry Zhao, Joseph Trasatti, Joshua Dickens, Matt Kaufer, Mike Trpcic, Minnia Feng, Neel Ajjarapu, Peter Vidani y Sean Fitzgerald.

Colaboradores

Investigación

Ahmed El-Kishky, AJ Ostrow, Alexander Wei, Andrei Gheorghe, Andrew Kondrich, Andrey Mishchenko, Anuj Nair, Behrooz Ghorbani, Brydon Eastman, Chak Li, Foivos Tsimpourlas, Francis Song, Giambattista Parascandolo,Gildas Chabot, Hessam Bagherinezhad, Haitang Hu, Hongyu Ren, Henry Aspegren, Hunter Lightman, Ilya Kostrikov, Ilge Akkaya, James Lennon, Jean Harb, Jonathan Ward, Kai Chen, Katy Shi, Kevin Liu, Kevin Yu, Manuka Stratta, Marvin Zhang, Mengyuan Yan,  Mostafa Rohaninejad, Noam Brown, Phoebe Thacker, Raz Goan, Reah Miyara, Spencer Papay, Taylor Gordon, Wenda Zhou, Wenlei Xie, Yash Patil, Yann Dubois, Youlong Cheng, Yushi Wang y Wyatt Thompson.

Más todos los colaboradores de o3.

Sistemas de Seguridad

Adam Kalai, Alex Beutel, Andrea Vallone, Andy Applebaum, David Robinson, Elizabeth Proehl, Evan Mays, Grace Zhao, Irina Kofman, Jason Phang, Joaquin Quinonero Candela, Joel Parish, Kevin Liu, Kristen Ying, Lama Ahmad, Leon Maksin, Leyton Ho, Meghan Shah, Michele Wang, Miles Wang, Phillip Guo, Olivia Watkins, Owen Campbell-Moore, Patrick Chao, Sam Toizer, Samuel Miserendino, Sandhini Agarwal, Tejal Patwardhan, Tina Sriskandarajah, Troy Peterson, Yaodong Yu y Yunyun Wang.

Implementación

Adam Koppel, Adam Wells, Adele Li, Andy Applebaum, Andrey Malevich, Andrew Duberstein, Andrew Howell, Anton Tananaev, Ashley Tyra, Brandon Walkin, Bryan Ashley, Cary Bassin, Cary Hudson, Cory Decareaux, Cristina Scheau, Derek Chen, Dibya Bhattacharjee, Drea Lopez, Eric Antonow, Eric Burke, Filippo Raso, Fotis Chantzis, Freddie Sulit, Harris Cohen, Heather Whitney, Jay Dixit, Jeffrey Han, Jen Robinson, Jessica Shieh, Joel Parish, Kan Wu, Kevin Gladstone, Kshitij Wadhwa, Leo Vandriel, Leyton Ho, Liang Chen, Madeline Christian, Mamie Rheingold, Matt Jones, Michelle Fradin, Mike McClay, Mingxuan Wang, Nacho Soto, Niko Felix, Patrick Delaney, Paul McMillan, Philip Pronin, Rodrigo Riaza Perez, Samuel Miserendino, Scott Ethersmith, Steven Baldwin, Thomas Dimson, Tomo Hiratsuka, Yaming Lin, Yara Khakbaz y Yining Chen.

Liderazgo

Akshay Nathan, Greg Brockman, Hannah Wong, Jakub Pachocki, Jerry Tworek, Johannes Heidecke, Josh Tobin, Liam Fedus, Mark Chen, Mia Glaese, Nick Turley, Sam Altman y Wojciech Zaremba