Lumaktaw sa pangunahing content
OpenAI

Pebrero 2, 2025

Paglabas

Pagpapakilala ng malalimang pananaliksik

Agent na gumagamit ng pangangatwiran para ma-synthesize ang malaking bilang ng online na impormasyon at kumpletuhin ang mga multi-step na gawain sa pananaliksik para sa iyo. Available sa mga user ng Pro ngayon, susunod ang Plus at Team.

Subukan sa ChatGPT(magbubukas sa bagong window)
Naglo-load…

Update noong Pebrero 10, 2026: Maaari mo nang ikonekta ang malalimang pananaliksik sa anumang MCP o app at limitahan ang mga paghahanap sa web sa mga pinagkakatiwalaang site, upang makapagpokus ka sa mga sangguniang na-authenticate at pasok sa pamantayang pang-industriya. Maaari mo na ring subaybayan ang pag-usad sa real-time at huminto upang magpahusay pa gamit ang mga follow-up na prompt o mga bagong sanggunian. In-update namin ang biswal na karanasan upang mas madali nang simulan, subaybayan, at suriin ang iyong pananaliksik mula simula hanggang dulo.

Update noong Hulyo 17, 2025: Puwede na ngayong maging mas malalim at mas malawak ang malalimang pananaliksik sa pamamagitan ng pag-access sa visual browser bilang bahagi ng agent ng ChatGPT. Para ma-access ang mga na-update na kakayahan na ito, piliin lang ang "agent mode" mula sa dropdown sa composer at ilagay ang iyong query nang direkta. Ang orihinal na functionality ng malalimang pananaliksik ay nananatiling available sa pamamagitan ng opsyong "malalimang pananaliksik" sa menu ng mga tool.

Update noong Abril 24, 2025: Malaki ang pagtaas ng dalas ng paggamit natin ng malalimang pananaliksik—Makakakuha na ngayon ang mga user ng Plus, Team, Enterprise, at Edu ng 25 na query bawat buwan, makakakuha ang mga user ng Pro ng 250, at makakakuha ang mga user ng Free ng 5. Posible ito sa pamamagitan ng bagong magaan na bersyon ng malalimang pananaliksik na pinapagana ng bersyon ng o4-mini, na idinisenyo para maging mas matipid sa gastos habang pinapanatili ang mataas na kalidad. Kapag naabot mo na ang iyong limitasyon para sa buong bersyon, awtomatikong lilipat ang iyong mga query sa magaan na bersyon.

Update noong Pebrero 25, 2025: Lahat ng user ng Plus ay puwede nang gumamit ng malalimang pananaliksik.

Update ng Pebrero 5, 2025: Available na ngayon ang malalimang pananaliksik sa mga user ng Pro sa United Kingdom, Switzerland, at European Economic Area.

Ngayon, inilulunsad namin ang malalimang pananaliksik sa ChatGPT, isang bagong agentic na kakayahan na kayang magsagawa ng multi-step na pananaliksik sa internet para sa mga kumplikadong gawain. Nagagawa nito sa loob ng sampung minuto ang mga bagay na aabutin ng maraming oras ng isang tao.

Ang malalimang pananaliksik ang susunod na agent ng OpenAI na kayang gumawa ng trabaho para sa iyo nang independent—ibigay mo lang ang prompt, at hahanapin, susuriin, at pagsasama-samahin ng ChatGPT ang daan-daang online na sanggunian para makabuo ng komprehensibong report sa antas ng research analyst. Pinapagana ng bersyon ng paparating na modelo ng OpenAI o3 na na-optimize para sa pag-browse sa web at pagsusuri ng data, ginagamit nito ang pangangatwiran para maghanap, mag-interpret, at mag-analisa ng napakaraming text, mga larawan, at mga PDF sa internet, na inaangkop kung kinakailangan bilang tugon sa impormasyong nakakasalamuha nito.

Ang kakayahang magsagawa ng pagse-senthesize ng kaalaman ay kinakailangan para gumawa ng bagong kaalaman. Dahil sa dahilan na ito, ang malalimang pananaliksik ay nagmamarka ng makabuluhang hakbang patungo sa aming mas malawak na layunin ng pagbuo ng AGI, na matagal na naming inisip na may kakayahang gumawa ng bagong siyentipikong pananaliksik.

Why we built deep research

Deep research is built for people who do intensive knowledge work in areas like finance, science, policy, and engineering and need thorough, precise, and reliable research. It can be equally useful for discerning shoppers looking for hyper-personalized recommendations on purchases that typically require careful research, like cars, appliances, and furniture. Every output is fully documented, with clear citations and a summary of its thinking, making it easy to reference and verify the information. It is particularly effective at finding niche, non-intuitive information that would require browsing numerous websites. Deep research frees up valuable time by allowing you to offload and expedite complex, time-intensive web research with just one query.

Deep research independently discovers, reasons about, and consolidates insights from across the web. To accomplish this, it was trained on real-world tasks requiring browser and Python tool use, using the same reinforcement learning methods behind OpenAI o1, our first reasoning model. While o1 demonstrates impressive capabilities in coding, math, and other technical domains, many real-world challenges demand extensive context and information gathering from diverse online sources. Deep research builds on these reasoning capabilities to bridge that gap, allowing it to take on the types of problems people face in work and everyday life.

How to use deep research

In ChatGPT, select ‘deep research’ in the message composer and enter your query. Tell ChatGPT what you need—whether it’s a competitive analysis on streaming platforms or a personalized report on the best commuter bike. You can attach files or spreadsheets to add context to your question. Once it starts running, a sidebar appears with a summary of the steps taken and sources used.

Deep research may take anywhere from 5 to 30 minutes to complete its work, taking the time needed to dive deep into the web. In the meantime, you can step away or work on other tasks—you’ll get a notification once the research is complete. The final output arrives as a report within the chat – in the next few weeks, we will also be adding embedded images, data visualizations, and other analytic outputs in these reports for additional clarity and context.

Compared to deep research, GPT‑4o is ideal for real-time, multimodal conversations. For multi-faceted, domain-specific inquiries where depth and detail are critical, deep research’s ability to conduct extensive exploration and cite each claim is the difference between a quick summary and a well-documented, verified answer that can be usable as a work product.

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.

Deep research

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.

Deep research responds to the prompt in a highly detailed manner, providing side-by-side country-specific data for both top 10 developed and top 10 developing countries for easy reference and comparison. It uses that information to offer detailed market-entry recommendations that are informed and usable.

Paano ito gumagana

Sinasanay ang malalimang pananaliksik gamit ang end-to-end pagpapatibay ng pag-aaral sa mga mahihirap na gawain sa pag-browse at pangangatwiran sa iba't ibang domain. Sa pamamagitan ng pagsasanay na iyon, natutunan nitong planuhin at isagawa ang multi-step na landas para mahanap ang data na kailangan nito, nagba-backtrack at tumutugon sa real-time na impormasyon kung kinakailangan. Kaya rin ng modelo na mag-browse sa mga file na in-upload ng user, mag-plot at mag-iterate sa mga graph gamit ang tool na Python, i-embed ang parehong mga binuong graph at mga larawan mula sa mga website sa mga tugon nito, at banggitin ang mga partikular na pangungusap o talata mula sa mga pinagmulan nito. Dahil sa pagsasanay na ito, naabot nito ang mga bagong antas sa bilang ng pampublikong pagsusuri na nakatuon sa mga totoong problema sa mundo.

Huling Pagsusulit sa Humanity

Sa Huling Pagsusulit sa Humanity⁠(magbubukas sa bagong window), ang kamakailang inilabas na ebalwasyon na sumusubok sa AI sa malawak na hanay ng mga paksa sa mga tanong sa antas ng eksperto, ang modelong nagpapagana ng malalim na pananaliksik ay nakakuha ng bagong pinakamataas na marka sa 26.6% na katumpakan. Ang pagsusulit na ito ay binubuo ng mahigit 3,000 tanong na may maraming pagpipilian at maikling sagot sa mahigit 100 asignatura mula sa lingguwistika hanggang sa siyensiya na may mataas na antas, mga klasiko hanggang sa ekolohiya. Kung ikukumpara sa OpenAI o1, lumitaw ang pinakamalaking pagsulong sa chemistry, humanities at social science, at mathematics. Ang modelong nagpapagana sa malalimang pananaliksik ay nagpakita ng isang mala-tao na pamamaraan sa pamamagitan ng epektibong paghahanap ng espesyal na impormasyon kung kinakailangan.

ModeloKatumpakan (%)
GPT-4o3.3
Grok-23.8
Claude 3.5 Sonnet4.3
Gemini Thinking6.2
OpenAI o19.1
DeepSeek-R1*9.4
OpenAI o3-mini (medium)*10.5
OpenAI o3-mini (mataas)*13.0
Malalimang pananaliksik sa OpenAI**26.6
* Ang modelo ay hindi multi-modal, sinuri lamang sa subset na text.
**may kasamang mga tool sa pag-browse + python

GAIA

Sa GAIA⁠(magbubukas sa bagong window)1, ang pampublikong benchmark na sumusuri sa AI gamit ang mga katanungan sa totoong mundo, ang modelo na nagpapalakas sa malalimang pananaliksik ay umabot sa bagong antas ng kahusayan (SOTA), nangunguna sa panlabas na leaderboard⁠(magbubukas sa bagong window). Dahil sumasaklaw ito sa tatlong antas ng kahirapan, ang matagumpay na pagkumpleto ng mga gawaing ito ay nangangailangan ng mga kakayahan kabilang ang pangangatwiran, kahusayan sa iba't ibang modal, pag-browse sa web, at kahusayan sa paggamit ng mga tool.

GAIA
Antas 1Antas 2Antas 3Avg.
Nakaraang SOTA(magbubukas sa bagong window)67.9267.4442.3163.64
Malalimang Pananaliksik (pass@1)74.2969.0647.667.36
Malalimang Pananaliksik (cons@64)78.6673.2158.0372.57

Mga halimbawa ng mga gawain ng 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.

[aksyon sa paghahanap]

Navigating search filters

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.

[aksyon sa pag-browse]

Reflecting on potential issues

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

[aksyon sa pag-browse]

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.

[aksyon sa paghahanap]

Pinpointing key features

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

[aksyon sa pag-browse]

Piecing together insights

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

[aksyon sa paghahanap]

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.

[aksyon sa paghahanap]

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.

[aksyon sa paghahanap]

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.

[aksyon sa pag-browse]

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.

[aksyon sa pag-browse]

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."

[aksyon sa pag-browse]

Evaluating library sources

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

[aksyon sa pag-browse]

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.

[aksyon sa pag-browse]

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.

[aksyon sa pag-browse]

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.

[aksyon sa pag-browse]

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.

[aksyon sa paghahanap]

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.

[aksyon sa paghahanap]

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.

[aksyon sa paghahanap]

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.

[aksyon sa paghahanap]

Mga Gawain sa Antas ng Eksperto

Sa panloob na pagsusuri ng mga gawain sa antas ng eksperto sa iba't ibang larangan, ang malalimang pananaliksik ay na-rate ng mga eksperto sa domain na nag-automate ng maraming oras ng mahirap at manu-manong pagsisiyasat. 

Antas ng Pagpasa Kumpara sa Pinakamataas na Tawag sa Tool
Antas ng PagpasaPinakamataas na Tawag sa Tool
Habang mas madalas i-browse at mag-isip ang modelo tungkol sa kanyang binabasa, mas nagiging mahusay ito, kaya mahalaga ang pagbibigay dito ng oras para mag-isip.
Mga halimbawa ng gawain sa antas ng eksperto
Oras na natipid sa gawain: 4 na oras

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)=kD p  +  CH′ b p 1+b p  .C(p) = k_D\,p \;+\; \frac{C'_H\,b\,p}{\,1 + b\,p\,}\,.

Here kDk_D is the Henry’s law coefficient for dissolution, CH′C'_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 CH′→0C'_H \to 0 as T→TgT \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,A′ bA pA  +  CH,B′ bB pB  1+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,i′bipi 1+∑jbjpj C_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, CH′C'_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.

Pag-unawa sa mga modelo ng sorption

Nangangalap ako ng impormasyon tungkol sa puro at halo-halong gas sorption sa mga glassy polymer, na nakatuon sa dual-mode sorption na modelo at pagtugon sa mga hamon sa mga hula sa pagmomodelo.

[aksyon sa paghahanap]

Pagtatasa ng bukas na pag-access

Sige, tingnan ko. Ang resulta mula sa MDPI tungkol sa sorption ng halo-halong gas sa mga glassy polymer ay malamang na bukas na pag-access.

[aksyon sa pag-browse]

[aksyon sa pag-browse]

Pagsusuri ng mga seksyon
Pinagsasama-sama ko ang mga pananaw mula sa Dual Mode Sorption na Modelo at ang pinalawig na pagsusuri nito sa MDPI paper.

[aksyon sa pag-browse]

Paglilinaw ng mga pangunahing katangian

Sinusuri ko ang lab report para maunawaan ang Henry’s law constant, Langmuir affinity constant, at Langmuir capacity constant, na naglalarawan ng gas sorption.

[aksyon sa pag-browse]

Pinagsasama-sama

Pinag-aaralan ko ang posibilidad na ang "Equation (3)" at "Equation (4)" ay puwedeng mga larawan o display ng formula at isinasaalang-alang ko ang pagkonsulta sa PDF o paghahanap ng mga naunang reperensya para mas maunawaan ang mga ito.

[aksyon sa pag-browse]

Pagkumpirma ng kaugnayan ng pamagat

Bine-verify ko kung ang dokumento mula sa Freeman at Koros (1980) ay partikular na tumutugma sa reference na "Model for sorption of mixed gases in glassy polymers" sa pamamagitan ng pagsuri sa abstract at pamagat nito.

[aksyon sa paghahanap]

Pagsusuri sa mga koneksyon ng artikulo

Napansin ko na ang resulta mula sa "pmc.ncbi.nlm.nih.gov" ay malamang na kapareho ng artikulo ng MDPI, at gusto kong malaman kung ipinapakita nito ang text o pinasimpleng bersyon.

[aksyon sa pag-browse]

[aksyon sa pag-browse]

[aksyon sa pag-browse]

Pagkolekta ng impormasyon

Nangangalap ako ng impormasyon tungkol sa puro at halo-halong gas sorption sa mga glassy polymer. Isa itong kritikal na hakbang sa pag-unawa sa gawi ng materyal sa ilalim ng iba't ibang kapaligiran ng gas.

[aksyon sa paghahanap]

Paghahambing ng gas sorption

Napansin ko na ang presensya ng carbon dioxide sa pinaghalong sangkap ay nakakaapekto sa sorption ng methane sa polimer, na binabawasan ang sorption ng methane kumpara sa senaryo ng purong gas.

[aksyon sa pag-browse]

Pag-uugnay ng mga konsepto

Pinag-iisipan ko kung paano puwedeng maiugnay ang terminong "pinalawak na dual mode equation mixture" sa mga dual mode superconducting cable equation. Ipinapakita nito ang potensyal para sa pagkonekta ng mga konsepto sa iba't ibang larangan.

[aksyon sa paghahanap]

Humihiling ng mga detalye ng pagsusuri

Binabanggit ko ang kahilingang repasuhin ang "Mga Teorya ng Sorption at Transportasyon sa Polymer Membrane."

[aksyon sa pag-browse]

Pagsusuri sa link ng PDF

Curious ako tungkol sa Resulta [2] at pag-explore sa snippet, na kinabibilangan ng pagpapalawig ng dual-mode sorption na modelo sa binary mixture at pagpapahayag ng konsentrasyon ng A sa mga tuntunin ng mga bahagyang presyon at constant.

[aksyon sa paghahanap]

Paghula ng paggawi ng sorption

Inaasahan ng modelong dual-mode na ang pagdadagdag ng pangalawang gas ay nakakabawas ng sorption sa pare-parehong bahagyang presyon, hindi tulad ng mga senaryo ng purong gas.

[aksyon sa pag-browse]

Pagkuha ng PDF

Nangangalap ako ng impormasyon ng PDF ng nature.com, posibleng mas lumang artikulo mula sa Yampol'ski, pero iniisip ko ang mga alternatibong mapagkukunan tulad ng repositoryo ng University of Texas sa Austin para sa snippet ng text.

[aksyon sa pag-browse]

Pagsusuri ng mga pagpipilian sa repositoryo

Natuklasan ko na maaaring hindi tama ang pagpapakita ng resulta ng repositoryo ng UT. Hindi tiyak ang paghahanap sa loob nito. Bilang kahalili, ang resulta [3] ay naglalaman ng snippet na naglalarawan sa modelo ng dual mode mixture sorption, na nagpapaliwanag ng mapagkumpitensyang epekto at ang kasapatan nito sa pagmomodelo ng pang-eksperimentong data.

[aksyon sa paghahanap]

Pagpapahusay ng pokus

Inaayos ko ang paraan ko para masiguro na nakatuon sa tamang konteksto ang paghahanap.

[aksyon sa paghahanap]

Pag-unawa sa mga modelo ng sorption

Idinedetalye ko ang dual-mode sorption na modelo para sa mga purong gas: Henry dissolving at Langmuir microvoid filling. Para sa mga halo-halong gas, binibigyang-diin ang mapagkumpitensyang sorption at mga hindi ideyal.

[aksyon sa paghahanap]

Galugarin ang hero.epa.gov

Sa pag-iisip tungkol sa posibleng buod o nilalaman ng hero.epa.gov.

[aksyon sa pag-browse]

Pagpapahusay ng modelo

Nangongolekta ako ng mga pananaw sa puro at halo-halong gas sorption, isinasaalang-alang ang mga salik tulad ng kumpetisyon, plasticization, at katatagan ng parameter. Pagsasama ng data ng halo-halong gas para sa mas tumpak na mga prediksyon.

[aksyon sa pag-browse]

Pagtugon sa mga hamon ng modelo ng dual sorption

Nakakaapekto sa mga prediksyon ang pag-uugnay ng mga parameter at kawalan ng natatanging solusyon. Puwedeng magdulot ng mga pagkakamali ang kawalan ng mga pagbabago sa kondisyon ng polimer.

[aksyon sa pag-browse]

Pagku-quantify ng paglihis

Kinu-quantify ko ang nonideal na CO₂–CH₄ solubility sa 6FDA-mPDA, para ipakita ang mga epekto ng halo-halong gas sa solubility. Ang mapagkumpitensyang sorption ay hindi ang tanging dahilan ng pagbaba ng permeability selectivity.

[aksyon sa pag-browse]

Pagsasama ng mga sanggunian

Nangangalap ako ng mga sitasyon, na nakatuon sa mga open-source na materyal tulad ng MDPI 2019 at Vopicka 2014, para suportahan ang talakayan tungkol sa mga pagkakaiba at hamon sa dual-mode na modelo para sa gas sorption sa mga polymeric membrane.

[aksyon sa pag-browse]

Pagmumungkahi ng mga seksyon

Nag-oorganisa ako ng mga seksyon tungkol sa puro vs halo-halong gas na sorption, sinisiyasat ang dual-mode sorption na modelo, at dinedetalye ang mga hamong tulad ng kawalan ng katiyakan ng parameter at hula ng halo-halong gas.

Pag-aayos ng content

Nakatuon ako sa modelo ng dual-mode sorption, na nagdedetalye ng mga paggawi ng puro at halo-halong gas sorption, at itinatampok ang mga pangunahing pagkakaiba at hamon gamit ang mga bullet point at nakabalangkas na mga seksyon para sa kalinawan.

[aksyon sa paghahanap]

Pagpili ng mga pagsipi

Sige, tingnan ko. Umaasa ako sa [3], [20], [22], at [21] para sa kanilang malinaw na pananaw sa dual-mode na sorption at mga pinaghalong gas.

Pagmamapa ng mga parameter

Pinagsasama-sama ko ang mga pangalan ng parameter para maiwasan ang kalituhan. Gamitin ang (k), (C_H'), at (b) para sa kalinawan. Detalyado at malinaw ang pagkaka-format ng mga equation para sa purong gas at mixture.

Pagtugon sa mga hamon

Tinatalakay ko ang mga multi-solution parameter fit, polymer plasticization, at temporal effect. Dahil sa mga detalyeng ito, nagiging mahirap ang pagpredict ng sorption ng purong gas at ng halo.

Pinagsasama-sama

Binubuo ko ang mga seksyon tungkol sa mga pagkakaiba ng sorption, ang dual-mode na modelo para sa mga purong gas, ang pagpapalawak nito sa mga halo-halong gas, at ang mga kaugnay na hamon. Ang pag-unlad na ito ay tila lohikal at epektibo.

Antas ng Pagpasa sa mga Gawain sa Antas ng Eksperto Batay sa Tinatayang Halaga ng Ekonomiya
Antas ng PagpasaTinatayang Halagang Pang-ekonomiya
Antas ng pagpasa sa mga gawain sa antas ng eksperto batay sa tinatayang oras
Antas ng PagpasaTinatayang Oras
Ang tinatayang pang-ekonomiyang halaga ng gawain ay mas nauugnay sa rate ng pagpasa kaysa sa bilang ng oras na aabutin ng tao – ang mga bagay na mahirap para sa mga modelo ay naiiba sa mga bagay na nakakaubos ng oras para sa mga tao.

Limitations

Deep research unlocks significant new capabilities, but it’s still early and has limitations. It can sometimes hallucinate facts in responses or make incorrect inferences, though at a notably lower rate than existing ChatGPT models, according to internal evaluations. It may struggle with distinguishing authoritative information from rumors, and currently shows weakness in confidence calibration, often failing to convey uncertainty accurately. At launch, there may be minor formatting errors in reports and citations, and tasks may take longer to kick off. We expect all these issues to quickly improve with more usage and time.

Access

Deep research in ChatGPT is currently very compute intensive. The longer it takes to research a query, the more inference compute is required. We are starting with a version optimized for Pro users today, with up to 100 queries per month. Plus and Team users will get access next, followed by Enterprise. We are still working on bringing access to users in the United Kingdom, Switzerland, and the European Economic Area. 

All paid users will soon get significantly higher rate limits when we release a faster, more cost-effective version of deep research powered by a smaller model that still provides high quality results. 

In the coming weeks and months, we’ll be working on the technical infrastructure, closely monitoring the current release, and conducting even more rigorous testing. This aligns with our principle of iterative deployment. If all safety checks continue to meet our release standards, we anticipate releasing deep research to Plus users in about a month.

Ano ang susunod

Available ngayon ang malalimang pananaliksik sa ChatGPT web, at ilalabas sa mga mobile at desktop app sa loob ng buwang ito. Sa kasalukuyan, puwedeng ma-access ng malalimang pananaliksik ang bukas na web at anumang i-upload na mga file. Sa hinaharap, magagawa mong kumonekta sa mas dalubhasang mga mapagkukunan ng data—palalawakin ang pag-access nito sa mga mapagkukunan na nakabatay sa subscription o panloob—para gawing mas matatag at naka-personalize ang output nito.

Sa hinaharap, nakikita namin na magsasama-sama ang mga agentic na karanasan sa ChatGPT para sa asynchronous na pananaliksik at aktwal na pagpapatupad sa totoong buhay. Ang kombinasyon ng malalimang pananaliksik, na kayang magsagawa ng asynchronous na online na pananaliksik, at ng Operator, na kayang gumawa ng aksyon sa totoong mundo, ay magbibigay-daan sa ChatGPT na isakatuparan ang mas sopistikadong mga gawain para sa iyo.

Pebrero 3, 2025 addendum: Nagsagawa kami ng mahigpit na pagsubok sa kaligtasan, mga pagsusuri sa kahandaan, at mga pagsusuri sa pamamahala sa naunang bersyon ng o3 na nagpapagana sa malalimang pananaliksik, na kinikilala ito bilang Katamtamang⁠(magbubukas sa bagong window) panganib. Nagsagawa rin kami ng karagdagang pagsubok sa kaligtasan para mas maunawaan ang mga karagdagang panganib na nauugnay sa kakayahan ng malalimang pananaliksik na mag-browse sa web, at nagdagdag kami ng mga bagong pagpapagaan. Patuloy naming susubukin nang lubusan at susubaybayan nang mabuti ang kasalukuyang limitadong paglabas. Ibabahagi namin ang aming mga insight sa kaligtasan at mga pananggalang para sa malalimang pananaliksik sa system card kapag pinalawak namin ang access sa mga user ng Plus.

Footnotes

  1. 1

    We found that the ground-truth answers for this dataset were widely leaked online and have blocked several websites or URLs accordingly to ensure a fair evaluation of the model.

Authors

OpenAI

Research Leads

Isa Fulford, Zhiqing Sun

Foundational Contributors

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

Core Contributors

Research

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, Vitchyr Pong

Deployment

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

Contributors

Research

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, Wyatt Thompson

+ all the contributors to o3.

Safety Systems

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, Yunyun Wang

Deployment

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, Yining Chen

Leadership

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