Pereiti prie pagrindinio turinio
OpenAI

2025 m. vasario 2 d.

Leidimas

Pristatome gilų tyrinėjimą

Agentas, kuris naudoja samprotavimą, kad susintetintų didelius kiekius informacijos internete ir atliktų daugiapakopes tyrimo užduotis už jus. Prieinama „Pro“ naudotojams šiandien.

Įkeliama...

2026 m. vasario 10 d. atnaujinimas: dabar galite susieti gilųjį tyrimą su bet kuria MCP arba programa ir apriboti interneto paieškas tik patikimomis svetainėmis, kad galėtumėte susitelkti į patvirtintus, pramonės standartus atitinkančius šaltinius. Dabar taip pat galite stebėti eigą realiuoju laiku ir įsiterpti, kad patikslintumėte naudodami tolesnes užklausas arba naujus šaltinius. Atnaujinome vaizdinę patirtį, todėl pradėti, stebėti ir peržiūrėti tyrimą nuo pradžios iki galo tapo lengviau.


2025 m. liepos 17 d. atnaujinimas: gilus tyrinėjimas dabar gali veikti dar giliau ir plačiau, turėdamas prieigą prie vizualinės naršyklės kaip „ChatGPT“ agento dalis. Norėdami pasiekti šias atnaujintas galimybes, tiesiog pasirinkite „agento režimą“ išskleidžiamajame meniu kūrimo priemonėje ir įveskite užklausą tiesiogiai. Pradinė gilaus tyrinėjimo funkcija išlieka prieinama per parinktį „gilus tyrinėjimas“ įrankių meniu.


2025 m. balandžio 24 d. atnaujinimas: žymiai padidiname dažnį, kuriuo galite naudoti gilų tyrinėjimą – „Plus“, „Team“, „Enterprise“ ir „Edu“ naudotojai dabar gauna 25 užklausas per mėnesį, „Pro“ naudotojai – 250, o nemokami naudotojai – 5. Tai tapo įmanoma dėl naujos supaprastintos gilaus tyrinėjimo versijos, kurią valdo „o4-mini“ versija, sukurta taip, kad būtų ekonomiškesnė, išlaikant aukštą kokybę. Kai pasieksite išsamiosios versijos limitą, jūsų užklausos automatiškai bus peradresuotos supaprastintai versijai.


2025 m. vasario 25 d. atnaujinimas: visi „Plus“ naudotojai dabar gali naudotis giliu tyrinėjimu.


2025 m. vasario 5 d. atnaujinimas: gilus tyrinėjimas dabar prieinamas „Pro“ naudotojams Jungtinėje Karalystėje, Šveicarijoje ir Europos ekonominėje erdvėje.


Šiandien „ChatGPT“ pristatome gilų tyrinėjimą – naują agentinę galimybę, atliekančią daugiapakopį tyrimą internete sudėtingoms užduotims. Tai, kas žmogui užtrukti daugybę valandų, atliekama per kelias dešimtis minučių.

Gilus tyrinėjimas yra kitas „OpenAI“ agentas, galintis dirbti už jus savarankiškai – jūs pateikiate raginimą, o „ChatGPT“ suras, išanalizuos ir susintetins šimtus internetinių šaltinių, kad sukurtų išsamią ataskaitą tyrimų analitiko lygiu. Valdomas būsimo „OpenAI o3“ modelio versijos, optimizuotos naršymui internete ir duomenų analizei, jis naudoja samprotavimą, kad ieškotų, interpretuotų ir analizuotų didžiulius kiekius teksto, vaizdų ir PDF failų internete, prireikus keisdamas kryptį reaguodamas į rastą informaciją.

Gebėjimas sintetinti žinias yra būtina sąlyga naujos žinioms kurti. Dėl šios priežasties gilus tyrinėjimas žymi svarbų žingsnį mūsų platesnio tikslo – sukurti AGI, kurį jau seniai įsivaizduojame kaip gebantį atlikti naujus mokslinius tyrimus – link.

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.

Kaip tai veikia

Gilus tyrinėjimas buvo mokomas naudojant tiesioginį pastiprinimo mokymąsi sudėtingoms naršymo ir samprotavimo užduotims įvairiose srityse. Per šį mokymą jis išmoko planuoti ir vykdyti daugiapakopę trajektoriją reikiamiems duomenims rasti, prireikus grįžti atgal ir reaguoti į realiuoju laiku gaunamą informaciją. Modelis taip pat geba naršyti naudotojo įkeltus failus, braižyti ir koreguoti grafikus naudodamas „Python“ įrankį, įterpti į atsakymus tiek sugeneruotus grafikus, tiek vaizdus iš interneto svetainių, bei cituoti konkrečius sakinius ar pastraipas iš šaltinių. Dėl šio mokymo jis pasiekia naujas aukštumas daugelyje viešų vertinimų, orientuotų į realaus pasaulio problemas.

Humanity's Last Exam

Humanity's Last Exam(atsidaro naujame lange), neseniai išleistame vertinime, kuris testuoja DI įvairiose srityse pagal eksperto lygio klausimus, modelis, valdantis gilų tyrinėjimą, pasiekia naują aukštumą – 26,6 proc. tikslumą. Šį testą sudaro daugiau nei 3 tūkst. klausimų su pasirenkamais atsakymais ir trumpais atsakymais iš daugiau nei 100 dalykų – nuo lingvistikos iki raketų mokslo, nuo klasikos iki ekologijos. Palyginti su „OpenAI o1“, didžiausias prieaugis pastebėtas chemijos, humanitarinių ir socialinių mokslų bei matematikos srityse. Modelis, valdantis gilų tyrinėjimą, pademonstravo į žmogų panašų požiūrį, prireikus efektyviai ieškodamas specializuotos informacijos.

ModelisTikslumas (%)
GPT-4o3,3
Grok-23,8
Claude 3.5 Sonnet4,3
Gemini Thinking6,2
OpenAI o19,1
DeepSeek-R1*9,4
„OpenAI o3-mini“ (vidutinis)*10,5
„OpenAI o3-mini“ (didelis)*13,0
„OpenAI“ gilus tyrinėjimas**26,6
* Modelis nėra multimodalinis, įvertintas tik teksto pogrupyje.
** su naršymo + „python“ įrankiais

GAIA

GAIA(atsidaro naujame lange)1, viešame palyginamajame standarte, vertinančiame DI pagal realaus pasaulio klausimus, modelis, valdantis gilų tyrinėjimą, pasiekia naują pažangiausią lygį (SOTA), atsiduradamas išorės lyderių lentelės(atsidaro naujame lange) viršuje. Apimant klausimus trijuose sudėtingumo lygiuose, sėkmingam šių užduočių atlikimui reikalingi gebėjimai, įskaitant samprotavimą, multimodalinį sklandumą, naršymą internete ir įgudimą naudotis įrankiais.

GAIA
1 lygis2 lygis3 lygisVid.
Ankstesnis SOTA(atsidaro naujame lange)67,9267,4442,3163,64
Gilus tyrinėjimas (pass@1)74,2969,0647,667,36
Gilus tyrinėjimas (cons@64)78,6673,2158,0372,57

GAIA užduočių pavyzdžiai

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.

[paieškos veiksmas]

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.

[naršymo veiksmas]

Reflecting on potential issues

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

[naršymo veiksmas]

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.

[paieškos veiksmas]

Pinpointing key features

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

[naršymo veiksmas]

Piecing together insights

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

[paieškos veiksmas]

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.

[paieškos veiksmas]

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.

[paieškos veiksmas]

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.

[naršymo veiksmas]

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.

[naršymo veiksmas]

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."

[naršymo veiksmas]

Evaluating library sources

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

[naršymo veiksmas]

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.

[naršymo veiksmas]

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.

[naršymo veiksmas]

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.

[naršymo veiksmas]

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.

[paieškos veiksmas]

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.

[paieškos veiksmas]

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.

[paieškos veiksmas]

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.

[paieškos veiksmas]

Eksperto lygio užduotys

Atlikus vidaus eksperto lygio užduočių vertinimą įvairiose srityse, srities ekspertai įvertino, kad gilus tyrinėjimas automatizavo daugybę valandų sudėtingo, rankinio tyrimo. 

Išlaikymo rodiklis lyginant su maksimaliu įrankių iškvietimų skaičiumi
Išlaikymo rodiklisMaksimalus įrankių iškvietimų skaičius
Kuo daugiau modelis naršo ir galvoja apie tai, ką naršo, tuo geriau jam sekasi, todėl svarbu duoti jam laiko pagalvoti.
Eksperto lygio užduočių pavyzdžiai
Sutaupyta laiko užduočiai: 4 val.

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.

Sorbcijos modelių supratimas

Renku informaciją apie grynų ir mišrių dujų sorbciją stikliškuose polimeruose, daugiausia dėmesio skirdamas dviejų režimų sorbcijos modeliui ir modeliavimo prognozių iššūkiams.

[paieškos veiksmas]

Atvirosios prieigos vertinimas

Gerai, pažiūrėkime. Rezultatas iš MDPI apie mišrių dujų sorbciją stikliškuose polimeruose greičiausiai yra atvirosios prieigos.

[naršymo veiksmas]

[naršymo veiksmas]

Skyrių nagrinėjimas surenku įžvalgas iš dviejų režimų sorbcijos modelio ir jo išplėstinės analizės MDPI straipsnyje.

[naršymo veiksmas]

Pagrindinių savybių tikslinimas

Nagrinėju laboratorijos ataskaitą, kad suprasčiau Henrio dėsnio konstantą, Langmuiro afiniteto konstantą ir Langmuiro talpos konstantą, kurios apibūdina dujų sorbciją.

[naršymo veiksmas]

Sudėliojimas

Svarstau galimybę, kad „(3) lygtis“ ir „(4) lygtis“ gali būti vaizdai arba formulių atvaizdavimai, ir svarstau pasikonsultuoti su PDF arba ieškoti ankstesnių nuorodų, kad geriau jas suprasčiau.

[naršymo veiksmas]

Pavadinimo tinkamumo patvirtinimas

Tikrinu, ar dokumentas iš Freeman ir Koros (1980) tiksliai atitinka nuorodą „Mišrių dujų sorbcijos stikliškuose polimeruose modelis“, peržiūrėdamas jo santrauką ir pavadinimą.

[paieškos veiksmas]

Straipsnių sąsajų nagrinėjimas

Pastebėjau, kad rezultatas iš „pmc.ncbi.nlm.nih.gov“ greičiausiai yra tas pats MDPI straipsnis, ir man smalsu pamatyti, ar jame pateikiamas tekstas, ar supaprastinta versija.

[naršymo veiksmas]

[naršymo veiksmas]

[naršymo veiksmas]

Informacijos rinkimas

Renku informaciją apie grynų ir mišrių dujų sorbciją stikliškuose polimeruose. Tai kritinis žingsnis siekiant suprasti medžiagos veikseną skirtingose dujų aplinkose.

[paieškos veiksmas]

Dujų sorbcijos palyginimas

Pastebėjau, kad anglies dioksido buvimas mišinyje veikia metano sorbciją polimere, sumažindamas metano sorbciją, palyginti su grynų dujų scenarijumi.

[naršymo veiksmas]

Sąvokų siejimas

Apgalvoju, kaip terminas „išplėstinė dviejų režimų lygties mišinio versija“ gali sietis su dviejų režimų superlaidžių kabelių lygtimis. Tai rodo potencialą susieti sąvokas tarp skirtingų sričių.

[paieškos veiksmas]

Peržiūros detalių užklausa

Fiksuoju prašymą peržiūrėti „Sorbcijos ir pernašos polimerinėse membranose teorijas“.

[naršymo veiksmas]

PDF nuorodos tikrinimas

Domiuosi [2] rezultatu ir nagrinėju ištrauką, kuri apima dviejų režimų sorbcijos modelio išplėtimą binariniam mišiniui ir A koncentracijos išreiškimą per dalinius slėgius bei konstantas.

[paieškos veiksmas]

Sorbcijos veiksenos prognozavimas

Dviejų režimų modelis numato, kad pridėjus antras dujas sorbcija sumažėja esant pastoviam daliniam slėgiui, skirtingai nei grynų dujų scenarijuose.

[naršymo veiksmas]

PDF gavimas

Renku informaciją apie „nature.com“ PDF, galbūt senesnį Yampol'ski straipsnį, bet svarstau apie alternatyvius šaltinius, pavyzdžiui, Teksaso universiteto Ostine saugyklą teksto ištraukai gauti.

[naršymo veiksmas]

Saugyklos parinkčių vertinimas

Aptikau, kad UT saugyklos rezultatas gali būti rodomas neteisingai. Paieška joje yra neaiški. Arba [3] rezultate yra ištrauka, aprašanti dviejų režimų mišinio sorbcijos modelį, paaiškinanti konkurencinį poveikį ir jo tinkamumą modeliuojant eksperimentinius duomenis.

[paieškos veiksmas]

Dėmesio tikslinimas

Koreguoju savo požiūrį, kad užtikrinčiau, jog paieška būtų nukreipta į tinkamą kontekstą.

[paieškos veiksmas]

Sorbcijos modelių supratimas

Detalizuoju dviejų režimų sorbcijos modelį grynoms dujoms: tirpumas pagal Henrio dėsnį ir Langmuiro mikroertmių užpildymas. Mišrioms dujoms pabrėžiama konkurencinė sorbcija ir neidealumai.

[paieškos veiksmas]

Tyrinėju hero.epa.gov

Svarstau apie hero.epa.gov galimą santrauką ar turinį.

[naršymo veiksmas]

Modelio tobulinimas

Renku įžvalgas apie grynų ir mišrių dujų sorbciją, atsižvelgdamas į tokius veiksnius kaip konkurencija, plastifikacija ir parametrų stabilumas. Įtraukiu mišrių dujų duomenis tikslesnėms prognozėms.

[naršymo veiksmas]

Dviejų režimų sorbcijos modelio iššūkių sprendimas

Parametrų susiejimas ir nevienareikšmiškumas daro įtaką prognozėms. Polimero būklės pokyčių nebuvimas gali lemti apsirikimus.

[naršymo veiksmas]

Nuokrypio kiekybinis įvertinimas

Kiekybiškai vertinu neidealų CO2-CH4 tirpumą 6FDA-mPDA, parodydamas mišrių dujų poveikį tirpumui. Konkurencinė sorbcija nėra vienintelė pralaidumo selektyvumo mažėjimo priežastis.

[naršymo veiksmas]

Nuorodų įtraukimas

Renku citatas, daugiausia dėmesio skirdamas atvirojo kodo medžiagai, tokiai kaip MDPI 2019 ir Vopicka 2014, kad pagrįsčiau diskusiją apie skirtumus ir iššūkius dviejų režimų dujų sorbcijos modelyje polimerinėse membranose.

[naršymo veiksmas]

Skyrių siūlymas

Organizuoju skyrius apie grynų ir mišrių dujų sorbciją, nagrinėju dviejų režimų sorbcijos modelį ir detalizuoju iššūkius, tokius kaip parametrų neapibrėžtumas ir mišrių dujų prognozavimas.

Turinio organizavimas

Dėmesį sutelkiu į dviejų režimų sorbcijos modelį, detalizuoju grynų ir mišrių dujų sorbcijos veikseną ir pabrėžiu pagrindinius skirtumus bei iššūkius naudodamas punktus ir susistemintus skyrius dėl aiškumo.

[paieškos veiksmas]

Citavimo pasirinkimas

Gerai, pažiūrėkime. Remiuosi [3], [20], [22] ir [21] dėl jų aiškių įžvalgų apie dviejų režimų sorbciją ir dujų mišinius.

Parametrų susiejimas

Dėlioju parametrų pavadinimus, kad išvengčiau painiavos. Laikausi (k), (C_H) ir (b) dėl aiškumo. Grynų dujų ir mišinių lygtys yra detalios ir aiškiai suformatuotos.

Iššūkių sprendimas

Nagrinėju kelių sprendimų parametrų pritaikymą, polimerų plastifikaciją ir laiko efektus. Dėl šių subtilybių grynų ir mišrių dujų sorbcijos prognozavimas tampa keblus.

Sudėliojimas

Sisteminu skyrius apie sorbcijos skirtumus, dviejų režimų modelį grynoms dujoms, jo išplėtimą mišrioms dujoms ir susijusius iššūkius. Ši seka atrodo logiška ir efektyvi.

Eksperto lygio užduočių išlaikymo rodiklis pagal numatomą ekonominę vertę
Išlaikymo rodiklisNumatoma ekonominė vertė
Eksperto lygio užduočių išlaikymo rodiklis pagal numatytas valandas
Išlaikymo rodiklisNumatytos valandos
Numatoma ekonominė užduoties vertė labiau koreliuoja su išlaikymo rodikliu nei valandų skaičiumi, kurį užtruktų žmogus – tai, kas modeliams atrodo sunku, skiriasi nuo to, kas žmonėms užima daug laiko.

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.

Kas toliau?

Gilus tyrinėjimas jau šiandien prieinamas „ChatGPT“ saityne, o mobiliosiose ir darbalaukio programose pasirodys per šį mėnesį. Šiuo metu gilaus tyrinėjimo modelis gali pasiekti atvirą saityną ir visus įkeltus failus. Ateityje galėsite prisijungti prie daugiau specializuotų duomenų šaltinių – išplėsdami prieigą prie prenumeruojamų ar vidinių išteklių – kad rezultatai būtų dar patikimesni ir labiau individualizuoti.

Žvelgdami toliau į ateitį, numatome, kad „ChatGPT“ susijungs agentinės patirtys, skirtos asinchroniniam, realaus pasaulio tyrimui ir vykdymui. Gilaus tyrinėjimo, galinčio atlikti asinchroninį internetinį tyrimą, ir „Operator“, galinčio imtis realių veiksmų, derinys leis „ChatGPT“ atlikti vis sudėtingesnes užduotis už jus.


2025 m. vasario 3 d. priedas: atlikome griežtą ankstyvosios „o3“ versijos, valdančios gilų tyrinėjimą, saugumo testavimą, pasirengimo vertinimą ir valdymo peržiūrą, ir nustatėme, kad ji kelia vidutinę(atsidaro naujame lange) riziką. Taip pat atlikome papildomus saugumo testus, kad geriau suprastume papildomą riziką, susijusią su gilaus tyrinėjimo galimybe naršyti internete, ir pridėjome naujų rizikos mažinimo priemonių. Toliau kruopščiai testuosime ir atidžiai stebėsime dabartinę ribotą versiją. Išplėtę prieigą „Plus“ naudotojams, sistemos kortelėje pasidalinsime savo saugumo įžvalgomis ir apsaugos priemonėmis, skirtomis giliam tyrinėjimui.

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 ir Zhiqing Sun

Foundational Contributors

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