Preskočite na glavno vsebino
OpenAI

2. februar 2025

Izdaja

Predstavljamo podrobno raziskovanje

Agent, ki uporablja sklepanje za sintezo velikih količin spletnih informacij in za izvajanje večkoračnih raziskovalnih nalog namesto vas. Danes na voljo uporabnikom Pro, kmalu zatem še uporabnikom Plus in Team.

Preizkusite v ChatGPT-ju(odpre se v novem oknu)
Nalaganje …

Posodobitev 10. februarja 2026: Zdaj lahko poglobljeno raziskovanje povežete s katerim koli protokolom za modelni kontekst (MCP) ali aplikacijo in omejite spletna iskanja na zaupanja vredna spletna mesta, da se lahko osredotočite na preverjene vire, skladne z industrijskimi standardi. Prav tako lahko zdaj v realnem času spremljate napredek in kadar koli prekinete postopek, da ga z nadaljnjimi pozivi ali novimi viri natančneje prilagodite. Posodobili smo vizualno izkušnjo, da je lažje začeti, spremljati in pregledati raziskovanje od začetka do konca.

Posodobitev z dne 17. julija 2025: Poglobljeno raziskovanje je zdaj mogoče še bolj poglobiti in razširiti z dostopom do vizualnega brskalnika kot dela agenta ChatGPT. Za dostop do teh posodobljenih zmogljivosti preprosto izberite »način agenta« v spustnem meniju v sestavljalcu in neposredno vnesite poizvedbo. Prvotna funkcionalnost poglobljenega raziskovanja ostaja na voljo prek možnosti »poglobljeno raziskovanje« v meniju orodij.

Posodobitev 24. aprila 2025: povečujemo pogostost uporabe poglobljenega raziskovanja. Uporabniki Plus, Team, Enterprise in Edu imajo zdaj na voljo 25 poizvedb na mesec, uporabniki Pro 250, uporabniki Free pa 5. To bo možno zaradi nove, lažje različice Deep Research, ki ga poganja različica o4-mini, ki je stroškovno učinkovitejša in visoke kakovosti. Ko dosežete omejitev na polni različici, se vaše poizvedbe samodejno preklopijo na lažjo različico.

Posodobitev 25. februarja 2025: vsi uporabniki Plus lahko zdaj uporabljajo poglobljeno raziskovanje.

Posodobitev 5. februarja 2025: Poglobljeno raziskovanje je zdaj na voljo uporabnikom Pro v Združenem kraljestvu, Švici in Evropskem gospodarskem prostoru.

Danes v ChatGPT‑ju lansiramo poglobljeno raziskovanje, novo agentno zmožnost, ki za zahtevne naloge na internetu izvaja večkoračne raziskave. V nekaj deset minutah opravi tisto, za kar bi človek potreboval več ur.

Deep Research je naslednji agent OpenAI, ki lahko samostojno opravlja delo namesto vas. Podate mu poziv, ChatGPT pa poišče, analizira in sintetizira stotine spletnih virov ter pripravi obsežno poročilo na ravni raziskovalnega analitika. Poganja ga različica prihajajočega modela OpenAI o3, optimizirana za brskanje po spletu in analizo podatkov. Uporablja sklepanje, da na internetu išče, interpretira in analizira ogromne količine besedil, slik in datotek PDF ter se po potrebi prilagaja glede na informacije, na katere naleti.

Sposobnost sinteze znanja je predpogoj za ustvarjanje novega znanja. Zato poglobljeno raziskovanje predstavlja pomemben korak k našemu širšemu cilju razviti AGI, ki si ga že dolgo predstavljamo kot sistem, zmožen ustvarjati izvirne znanstvene raziskave.

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.

Kako deluje

Poglobljeno raziskovanje je bilo trenirano z metodo učenja s procesom prilagajanja od začetka do konca na zahtevnih nalogah brskanja in sklepanje v različnih domenah. S tem treningom se je naučilo načrtovati in izvajati večkoračno pot iskanja podatkov, ki jih potrebuje, po potrebi pa se vračati nazaj in se sproti odzivati na nove informacije. Model lahko brska tudi po uporabnikovo naloženih datotekah, riše in iterira grafe z uporabo orodja python, v svoje odzive vdeluje tako ustvarjene grafe kot slike s spletnih mest ter navaja točno določene stavke ali odlomke iz svojih virov. Zaradi tega treninga dosega nove najvišje rezultate na številnih javnih evalvacijah, osredotočenih na resnične probleme.

Humanity's Last Exam

Na testu »Humanity’s Last Exam«⁠(odpre se v novem oknu), nedavno objavljeni evalvaciji, ki UI testira na strokovni ravni vprašanj iz širokega obsega področij, je model, ki poganja poglobljeno raziskovanje, dosegel nov rekord s 26,6 % natančnostjo. Ta test vsebuje več kot 3.000 vprašanj izbirnega tipa in s kratkimi odgovori z več kot 100 področij od jezikoslovja do raketne znanosti in antičnih študij do ekologije. V primerjavi z OpenAI o1 so se največji napredki pokazali v kemiji, humanistiki in družboslovju ter matematiki. Model, ki poganja poglobljeno raziskovanje, je pokazal človeški pristop s tem, da je po potrebi uspešno našel specializirane informacije.

ModelNatančnost (%)
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 (high)*13,0
OpenAI poglobljeno raziskovanje**26,6
* Model ni večmodalen, ocenjen na podmnožici samo z besedilom.
**z brskanjem + orodja python

GAIA

Na GAIA⁠(odpre se v novem oknu)1, javnem merilu učinkovitosti, ki ocenjuje UI na vprašanjih iz resničnega sveta, model, ki poganja poglobljeno raziskovanje, dosega novo stanje najvišje zmogljivosti (SOTA) in se uvršča na vrh zunanje lestvice⁠(odpre se v novem oknu). Ker zajema vprašanja treh ravni zahtevnosti, uspešno reševanje teh nalog zahteva zmožnosti, kot so sklepanje, multimodalno razumevanje, brskanje po spletu in veščine uporabe orodij.

GAIA
Raven 12. stopnjaRaven 3Povp.
Predhodna vrhunska tehnologija(odpre se v novem oknu)67,9267,4442,3163,64
Poglobljeno raziskovanje (pass@1)74,2969,0647,667,36
Poglobljeno raziskovanje (cons@64)78,6673,2158,0372,57

Primeri nalog 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.

[dejanje iskanja]

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.

[dejanje brskanja]

Reflecting on potential issues

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

[dejanje brskanja]

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.

[dejanje iskanja]

Pinpointing key features

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

[dejanje brskanja]

Piecing together insights

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

[dejanje iskanja]

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.

[dejanje iskanja]

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.

[dejanje iskanja]

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.

[dejanje brskanja]

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.

[dejanje brskanja]

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."

[dejanje brskanja]

Evaluating library sources

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

[dejanje brskanja]

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.

[dejanje brskanja]

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.

[dejanje brskanja]

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.

[dejanje brskanja]

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.

[dejanje iskanja]

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.

[dejanje iskanja]

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.

[dejanje iskanja]

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.

[dejanje iskanja]

Naloge na strokovni ravni

Pri interni evalvaciji strokovnih nalog na več področjih so strokovnjaki ocenili, da je poglobljeno raziskovanje avtomatiziralo več ur zahtevnega ročnega raziskovanja. 

Stopnja uspešnosti v primerjavi z največjim številom priklicev orodja
Stopnja uspešnostiNajveč priklicev orodja
Več ko model brska in razmišlja o tem, kar brska, boljše rezultate dosega, zato je pomembno, da mu damo čas za razmislek.
Primeri nalog na strokovni ravni
Prihranek časa pri nalogi: 4 ure

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.

Razumevanje modelov sorpcije

Zbiram informacije o sorpciji čistih in mešanih plinov v steklastih polimerih, osredotočam se na dvojni model sorpcije in se lotevam izzivov pri napovedovanju modelov.

[dejanje iskanja]

Presoja odprtega dostopa

V redu, pa poglejmo. Rezultat MDPI o sorpciji mešanih plinov v steklastih polimerih je verjetno odprto dostopen.

[dejanje brskanja]

[dejanje brskanja]

Pregledovanje sekcij
Povzemam vpoglede iz dvojnega modela sorpcije in njegove razširjene analize v članku MDPI.

[dejanje brskanja]

Poenostavitev ključnih lastnosti

Preučujem laboratorijsko poročilo, da bi razumel Henryjevo konstanto, Langmuirjevo afinitetno konstanto in Langmuirjevo kapacitetno konstanto, ki opisujejo sorpcijo plinov.

[dejanje brskanja]

Sestavljanje celote

Preučujem možnost, da sta "enačba (3)" in "enačba (4)" morda sliki ali prikaza formul, in razmišljam o pregledu PDF-ja ali iskanju starejših referenc, da bi ju bolje razumeli.

[dejanje brskanja]

Potrditev ustreznosti naslova

Preverjam, ali se dokument Freemana in Korosa (1980) natančno ujema z referenco »Model za sorpcijo mešanih plinov v steklenih polimerih«, tako da preverim njegov povzetek in naslov.

[dejanje iskanja]

Preučevanje povezav med članki

Opazil sem, da je rezultat s »pmc.ncbi.nlm.nih.gov« verjetno isti članek MDPI, in zanima me, ali vsebuje celotno besedilo ali poenostavljeno različico.

[dejanje brskanja]

[dejanje brskanja]

[dejanje brskanja]

Zbiranje informacij

Zbiram informacije o sorpciji čistih in mešanih plinov v steklastih polimerih. To je ključen korak za razumevanje obnašanja materiala v različnih okoljih plinov.

[dejanje iskanja]

Primerjava sorpcije plinov

Opazil sem, da prisotnost ogljikovega dioksida v zmesi vpliva na sorpcijo metana v polimeru, saj zmanjša njegovo sorpcijo v primerjavi s scenarijem s čistimi plini.

[dejanje brskanja]

Povezovanje konceptov

Premišljujem, kako bi se lahko izraz »extended dual mode equation mixture« povezoval z enačbami za dvojnonačinski superprevodniški kabel. To nakazuje možnost povezovanja konceptov med različnimi področji.

[dejanje iskanja]

Zahteva za podrobnosti pregleda

Zabeležujem zahtevo za pregled »Teorij sorpcije in transporta v polimerni membrani«.

[dejanje brskanja]

Preverjanje povezave do PDF-a

Zanima me rezultat [2] in preučujem odlomek, ki vključuje razširitev dvojnega modela sorpcije na binarno zmes ter izražanje koncentracije A glede na parcialne tlake in konstante.

[dejanje iskanja]

Napovedovanje obnašanja pri sorpciji

Dvojni model predvideva, da dodatek drugega plina zmanjša sorpcijo pri konstantnem parcialnem tlaku, kar je drugače kot pri scenarijih s čistimi plini.

[dejanje brskanja]

Prenos datoteke PDF

Zbiram informacije iz datoteke PDF na nature.com, verjetno starejšega članka Yampol'skega, razmišljam pa tudi o alternativnih virih, kot je repozitorij University of Texas at Austin, zaradi iskanja besedilnega odlomka.

[dejanje brskanja]

Ocenjevanje možnosti repozitorijev

Ugotovil sem, da se rezultat iz repozitorija UT morda ne prikaže pravilno. Iskanje v njem je negotovo. Na drugi strani rezultat [3] vsebuje odlomek, ki opisuje dvojni model sorpcije zmesi, razlaga konkurenčne učinke in ustreznost modela pri opisovanju eksperimentalnih podatkov.

[dejanje iskanja]

Izostritev fokusa

Prilagajam svoj pristop, da zagotovim, da iskanje zadene pravi kontekst.

[dejanje iskanja]

Razumevanje modelov sorpcije

Podrobno opisujem dvojni način sorpcijskega modela za čiste pline: Henryjevo raztapljanje in Langmuirjevo polnjenje mikropraznin. Pri mešanih plinih sta v ospredju konkurenčna sorpcija in neidealnosti.

[dejanje iskanja]

Raziskovanje strani hero.epa.gov

Premišljujem o potencialnem izvlečku ali vsebini na hero.epa.gov.

[dejanje brskanja]

Izpopolnjevanje modela

Zbiram vpoglede o sorpciji čistih in mešanih plinov, upoštevam dejavnike, kot so konkurenca, plastifikacija in stabilnost parametrov. Vključevanje podatkov o mešanih plinih omogoča natančnejše napovedi.

[dejanje brskanja]

Naslavljanje izzivov modela dvojne sorpcije

Napovedi vpliva povezovanja parametrov in ne-enoličnosti. Odsotnost sprememb stanja polimera lahko privede do spregledov.

[dejanje brskanja]

Kvantificiranje odstopanj

Kvantificiram neidealno topnost CO₂-CH₄ v 6FDA-mPDA ter prikazujem učinke mešanih plinov na topnost. Konkurenčna sorpcija ni edini vzrok za upad selektivnosti prepustnosti.

[dejanje brskanja]

Vključevanje referenc

Zbiram citate, osredotočam se na odprtokodne materiale, kot sta MDPI 2019 in Vopicka 2014, da podprem razpravo o razlikah in izzivih dvojnega modela sorpcije plinov v polimernih membranah.

[dejanje brskanja]

Predlaganje sekcij

Urejam sekcije o sorpciji čistih in mešanih plinov, raziskujem dvojni model sorpcije in opisujem izzive, kot so negotovost parametrov in napovedovanje mešanih plinov.

Organiziranje vsebine

Osredotočam se na dvojni model sorpcije, opisujem obnašanje sorpcije čistih in mešanih plinov ter izpostavljam ključne razlike in izzive z alinejami in strukturiranimi sekcijami za večjo jasnost.

[dejanje iskanja]

Izbira navedkov

V redu, pa poglejmo. Črpam iz [3], [20], [22] in [21] zaradi njihovih jasnih vpogledov v dvojni model sorpcije in zmesi plinov.

Zarisovanje parametrov

Sestavljam imena parametrov, da se izognem zmedi. Zaradi jasnosti ostajam pri (k), (C_H') in (b). Enačbe za čiste pline in zmesi so podrobne in jasno oblikovane.

Soočanje z izzivi

Ukvarjam se s prileganjem parametrov z več rešitvami, plastifikacijo polimerov in časovnimi učinki. Ta zapletenost otežuje napovedovanje sorpcije čistih in mešanih plinov.

Sestavljanje celote

Urejanje segmentov o razlikah v sorpciji, dvojnem modelu sorpcije za čiste pline, njegovi razširitvi na mešane pline in pripadajočih izzivih. Ta potek se zdi logičen in učinkovit.

Stopnja uspešnosti pri nalogah na strokovni ravni glede na ocenjeno ekonomsko vrednost
Stopnja uspešnostiOcenjena ekonomska vrednost
Stopnja uspešnosti pri nalogah na strokovni ravni glede na predviden čas
Stopnja uspešnostiPredviden čas
Ocenjena ekonomska vrednost naloge je bolje povezana s stopnjo uspešnosti kot s številom ur, ki bi jih človek potreboval: naloge, ki so modelom težke, so drugačne od tistih, ki so za ljudi časovno potratne.

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.

Kaj sledi

Poglobljeno raziskovanje je danes na voljo v spletnem ChatGPT‑ju, v roku meseca pa bo uvedeno tudi v mobilnih in namiznih aplikacijah. Trenutno ima poglobljeno raziskovanje dostop do odprtega spleta in vseh naloženih datotek. V prihodnje ga boste lahko povezali z bolj specializiranimi viri podatkov, kar bo razširilo njegov dostop do naročniških ali internih virov in s tem naredilo njegov izhod še bolj robusten in prilagojen.

Naša vizija prihodnosti je, da bodo agentni sistemi v ChatGPT‑ju poenoteno omogočali asinhrono raziskovanje resničnega sveta. Kombinacija poglobljenega raziskovanja, ki izvaja asinhrono spletno preiskovanje, in Operatorja, ki deluje v resničnem svetu, bo ChatGPT omogočila, da bo namesto vas opravljal vse bolj zapletene naloge.

Dodatek z dne 3. februarja 2025: Izvedli smo stroge varnostne preizkuse, ocene pripravljenosti in preglede upravljanja zgodnje različice o3, ki omogoča poglobljeno raziskovanje, in jo opredelili kot srednje⁠(odpre se v novem oknu) tveganje. Izvedli smo tudi dodatne varnostne preizkuse, da bi bolje razumeli dodatna tveganja, povezana z zmožnostjo poglobljenega raziskovanja brskanja po spletu, in dodali smo nove blažilne ukrepe. Še naprej bomo temeljito testirali in pozorno spremljali trenutno omejeno izdajo. Naše varnostne vpoglede in zaščitne ukrepe za poglobljeno raziskovanje bomo delili v sistemski kartici, ko bomo razširili dostop na uporabnike 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 in Zhiqing Sun

Foundational Contributors

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