Preskočite na glavni sadržaj
OpenAI

2. veljače 2025.

Izdanje

Predstavljamo dubinsko istraživanje

Agent koji upotrebom zaključivanja sažima velike količine mrežnih informacija i za vas obavlja istraživačke zadatke u više koraka. Dostupno korisnicima plana Pro već danas, a naknadno i korisnicima planova Plus i Team.

Isprobajte ChatGPT(otvara se u novom prozoru)
Učitavanje…

Ažuriranje od 10. veljače 2026.: Sada možete povezati dubinsko istraživanje s bilo kojim MCP-om ili aplikacijom i ograničiti internetska pretraživanja na pouzdane mrežne lokacije, kako biste se mogli usredotočiti na provjerene, industrijski standardne izvore. Također možete pratiti napredak u stvarnom vremenu i prekinuti kako biste istraživanje doradili uz naknadne upite ili nove izvore. Ažurirali smo vizualno iskustvo kako bi vam bilo lakše započeti, pratiti i pregledati vaše istraživanje od početka do kraja.

Dodatak od 17. srpnja 2025.: Dubinsko istraživanje sad može ići još dublje i šire zahvaljujući vizualnom pregledniku kao dijelu funkcije agenta ChatGPT. Da biste pristupili tim proširenim mogućnostima, jednostavno u padajućem izborniku u sastavljaču poruke odaberite „način rada agenta” i izravno unesite svoj upit. Izvorna funkcionalnost dubinskog istraživanja i dalje je dostupna putem opcije „dubinsko istraživanje” u izborniku alata.

Ažuriranje 24. travnja 2025.: značajno povećavamo učestalost korištenja dubinskog istraživanja — Team, Enterprise, Edu i Plus korisnici sada dobivaju 25 upita mjesečno, Pro korisnici 250, a Free korisnici 5. Ovo je omogućeno novom 'laganom' verzijom dubinskog istraživanja pokretanom verzijom o4-mini, dizajniranom da bude isplativija, ali uz očuvanje visoke kvalitete. Kada dosegnete svoje ograničenje za punu verziju, vaši će se upiti automatski prebaciti na laganu verziju.

Dodatak od 25. veljače 2025.: Svi korisnici plana Plus sad mogu koristiti dubinsko istraživanje.

Dodatak od 5. veljače 2025.: Dubinsko istraživanje sad je dostupno korisnicima plana Pro u Ujedinjenom Kraljevstvu, Švicarskoj i Europskom gospodarskom prostoru.

Danas pokrećemo dubinsko istraživanje u ChatGPT‑u, novu mogućnost agenta koja provodi istraživanje na internetu u više faza kako bi obavila složenije zadatke. Ono postiže u nekoliko desetaka minuta ono što bi čovjeku oduzelo mnogo sati. U nekoliko desetaka minuta postiže ono što bi čovjeku oduzelo mnogo sati.

Dubinsko istraživanje novi je agent OpenAI-ja koji može samostalno odraditi posao umjesto vas – zadate mu upit, a ChatGPT će pronaći, analizirati i objediniti stotine mrežnih izvora kako bi izradio sveobuhvatno izvješće na razini istraživačkog analitičara. Pokreće ga inačica nadolazećeg modela OpenAI o3, optimizirana za pregledavanje weba i analizu podataka, koja koristi rezoniranje kako bi pretraživala, tumačila i analizirala goleme količine teksta, slika i PDF-ova na internetu te se pritom po potrebi prilagođavala informacijama na koje nailazi.

Sposobnost sinteze znanja preduvjet je za stvaranje novog znanja. Iz tog razloga, dubinsko istraživanje predstavlja značajan korak prema našem širem cilju razvoja AGI, koju smo dugo zamišljali kao sposobnu za stvaranje novih znanstvenih istraživanja.

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 funkcionira

Dubinsko istraživanje trenirano je korištenjem end-to-end učenja putem povratnih informacija na zahtjevnim zadacima pretraživanja i rezoniranja u različitim domenama. Kroz tu obuku naučilo je izraditi i izvršiti plan u više koraka kako bi pronašlo potrebne podatke, vraćajući se i reagirajući na informacije u stvarnom vremenu gdje je to potrebno. Model također može pregledavati datoteke koje prenesete, izraditi i uređivati grafove pomoću alata python, ugraditi izrađene grafove i slike s web-stranica u svoje odgovore te navoditi konkretne rečenice ili odlomke iz svojih izvora. Kao rezultat ove obuke, doseže nove vrhunce u brojnim javnim evaluacijama usmjerenim na probleme iz stvarnog svijeta.

Humanity's Last Exam

Na Humanity’s Last Exam⁠(otvara se u novom prozoru), nedavno objavljenoj evaluaciji koja testira umjetnu inteligenciju u širokom rasponu tema na stručnim pitanjima, model koji pokreće dubinska istraživanja postiže novi rekord s točnošću od 26,6 %. Taj se test sastoji od preko 3000 pitanja s višestrukim izborom i kratkim odgovorima iz više od 100 tema, od lingvistike do raketne znanosti, od klasika do ekologije. U usporedbi s modelom OpenAI o1, najveći napredak zabilježen je u kemiji, humanističkim i društvenim znanostima te matematici. Model koji pokreće dubinska istraživanja pokazao je pristup sličan ljudskom, učinkovito tražeći specijalizirane informacije kad je to potrebno.

ModelTočnost (%)
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 (visoko)*13,0
OpenAI dubinsko istraživanje**26,6
* Model nije višemodalan, evaluiran na tekstualnom podskupu.
** s pregledavanjem + Python alatima

GAIA

Na GAIA⁠(otvara se u novom prozoru)1, javnom referentnom testu koji procjenjuje umjetnu inteligenciju na stvarnim pitanjima, model koji pokreće dubinska istraživanja doseže novi vrhunac (SOTA), zauzimajući prvo mjesto na vanjskoj ljestvici⁠(otvara se u novom prozoru). Obuhvaćajući pitanja na tri razine težine, uspješno izvršavanje ovih zadataka zahtijeva sposobnosti poput rezoniranja, multimodalne fluentnosti, pretraživanja interneta i vještine korištenja alata.

GAIA
Razina 1Razina 2Razina 3Prosj.
Prethodna SOTA(otvara se u novom prozoru)67,9267,4442,3163,64
Duboko istraživanje (pass@1)74,2969,0647,667,36
Dubinsko istraživanje (cons@64)78,6673,2158,0372,57

Primjeri zadataka 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.

[pretraživačka radnja]

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.

[pregledaj radnju]

Reflecting on potential issues

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

[pregledaj radnju]

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.

[pretraživačka radnja]

Pinpointing key features

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

[pregledaj radnju]

Piecing together insights

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

[pretraživačka radnja]

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.

[pretraživačka radnja]

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.

[pretraživačka radnja]

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.

[pregledaj radnju]

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.

[pregledaj radnju]

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."

[pregledaj radnju]

Evaluating library sources

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

[pregledaj radnju]

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.

[pregledaj radnju]

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.

[pregledaj radnju]

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.

[pregledaj radnju]

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.

[pretraživačka radnja]

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.

[pretraživačka radnja]

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.

[pretraživačka radnja]

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.

[pretraživačka radnja]

Zadaci na stručnoj razini

U internom vrednovanju zadataka na stručnoj razini iz različitih područja, stručnjaci su procijenili dubinsko istraživanje kao rješenje koje automatizira višesatno, zahtjevno ručno istraživanje. 

Stopa prolaza u odnosu na maksimalni broj poziva alata
Stopa prolazaMaksimalni broj poziva alata
Što više model pregledava i razmišlja o onome što pregledava, to bolje radi, zbog čega je važno dati mu vremena za razmišljanje.
Primjeri zadataka na razini stručnjaka
Ušteđeno vrijeme na rješavanju zadatka: 4 sata

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.

Razumijevanje modela sorpcije

Prikupljam informacije o sorpciji čistih i miješanih plinova u staklastim polimerima, usredotočujući se na model sorpcije s dvorežimskim načinom rada i rješavanje izazova u predviđanjima modeliranja.

[pretraživačka radnja]

Procjena otvorenog pristupa

U redu, da vidim. Rezultat iz MDPI-ja o sorpciji miješanih plinova u staklastim polimerima vjerojatno je otvorenog pristupa.

[pregledaj radnju]

[pregledaj radnju]

Pregled dijelova
Prikupljam uvide iz dvorežimskog modela sorpcije i njegove proširene analize u MDPI-jevu radu.

[pregledaj radnju]

Razjašnjavanje ključnih svojstava

Pregledavam laboratorijski izvještaj kako bih razumio Henryjevu konstantu zakona, Langmuirovu konstantu afiniteta i Langmuirovu konstantu kapaciteta, koje opisuju sorpciju plinova.

[pregledaj radnju]

Sastavljanje

Razmatram mogućnost da su „Jednadžba (3)” i „Jednadžba (4)” slike ili prikazi formula te razmišljam o konzultiranju PDF-a ili pretraživanju ranijih referenci kako bih ih bolje razumio.

[pregledaj radnju]

Potvrđivanje relevantnosti naslova

Provjeravam odgovara li dokument Freemana i Korosa (1980.) konkretno referenci „Model za sorpciju miješanih plinova u staklastim polimerima” provjerom njegovog sažetka i naslova.

[pretraživačka radnja]

Ispitivanje veza članaka

Primijetio sam da je rezultat s „pmc.ncbi.nlm.nih.gov” vjerojatno isti MDPI članak, i zanima me prikazuje li tekst ili pojednostavljenu verziju.

[pregledaj radnju]

[pregledaj radnju]

[pregledaj radnju]

Prikupljanje informacija

Prikupljam informacije o sorpciji čistih i miješanih plinova u staklastim polimerima. Ovo je ključan korak u razumijevanju ponašanja materijala u različitim plinskim okruženjima.

[pretraživačka radnja]

Usporedba plinske sorpcije

Primijetio sam da prisutnost ugljikova dioksida u smjesi utječe na sorpciju metana u polimeru, smanjujući sorpciju metana u usporedbi sa scenarijem čistog plina.

[pregledaj radnju]

Povezivanje koncepata

Razmišljam o tome kako bi se izraz „proširena jednadžba dvorežimskog modela za mješavine” mogao povezivati s jednadžbama dvorežimskog supravodljivog kabela. Ovo pokazuje potencijal za povezivanje koncepata kroz različita područja.

[pretraživačka radnja]

Zahtjev za detalje pregleda

Bilježim zahtjev za pregled „Teorije sorpcije i transporta u polimernoj membrani”.

[pregledaj radnju]

Provjera PDF poveznice

Zanima me Rezultat [2] i istražujem isječak, koji uključuje proširenje modela sorpcije s dvorežimskim načinom rada na binarnu smjesu i izražavanje koncentracije A u terminima parcijalnih tlakova i konstanti.

[pretraživačka radnja]

Predviđanje ponašanja sorpcije

Dvorežimski model predviđa da dodavanje drugog plina smanjuje sorpciju pri konstantnom parcijalnom tlaku, za razliku od scenarija s čistim plinovima.

[pregledaj radnju]

Dohvaćanje PDF-a

Prikupljam informacije iz PDF-a na nature.com, vjerojatno starijeg Yampolskijeva članka, ali razmatram i alternativne izvore poput repozitorija Sveučilišta u Teksasu u Austinu radi pronalaska relevantnog isječka teksta.

[pregledaj radnju]

Procjena opcija repozitorija

Otkrio sam da se rezultat UT repozitorija možda ne prikazuje ispravno. Pretraživanje unutar njega je neizvjesno. Alternativno, rezultat [3] sadrži isječak koji opisuje dvorežimski model sorpcije smjese, objašnjavajući konkurentske učinke i njegovu prikladnost u modeliranju eksperimentalnih podataka.

[pretraživačka radnja]

Dorada fokusa

Prilagođavam svoj pristup kako bih osigurao da pretraga cilja pravi kontekst.

[pretraživačka radnja]

Razumijevanje modela sorpcije

Detaljno opisujem model sorpcije s dvostrukim načinom rada za čiste plinove: Henryjevo otapanje i Langmuirovo punjenje mikrošupljina. Za miješane plinove ističu se kompetitivna sorpcija i neidealnosti.

[pretraživačka radnja]

Istražujem hero.epa.gov

Razmišljam o mogućem sažetku ili sadržaju za hero.epa.gov.

[pregledaj radnju]

Rafiniranje modela

Prikupljam uvide o sorpciji čistih i miješanih plinova, uzimajući u obzir čimbenike poput konkurencije, plastifikacije i stabilnosti parametara. Uključivanje podataka o mješavinama plinova za preciznija predviđanja.

[pregledaj radnju]

Rješavanje izazova dvorežimskog modela sorpcije

Predviđanja utjecaja spajanja parametara i nejedinstvenosti. Izostanak promjena u stanju polimera može dovesti do previda.

[pregledaj radnju]

Kvantificiranje odstupanja

Kvantificiram neidealnu topljivost CO₂-CH₄ u polimeru 6FDA-mPDA i prikazujem kako mješavine plinova utječu na topljivost. Konkurentna sorpcija nije jedini razlog pada selektivnosti propusnosti.

[pregledaj radnju]

Uključivanje referenci

Prikupljam citate, s naglaskom na open-source literaturu poput radova MDPI 2019. i Vopicka 2014., u svrhu potkrepljivanja rasprave o razlikama i izazovima modela sorpcije plinova s dvorežimskim načinom rada u polimernim membranama.

[pregledaj radnju]

Predlaganje odjeljaka

Organiziram odjeljke o sorpciji čistog i miješanog plina, istražujem model sorpcije s dvorežimskim načinom rada i detaljno opisujem izazove poput nesigurnosti parametara i predviđanja miješanih plinova.

Organiziranje sadržaja

Usredotočujem se na model sorpcije s dvorežimskim načinom rada, detaljno opisujući ponašanje sorpcije čistih i miješanih plinova te ističući ključne razlike i izazove pomoću nabrajanja i strukturiranih odjeljaka radi jasnoće.

[pretraživačka radnja]

Odabir citata

U redu, da vidim. Oslanjam se na [3], [20], [22] i [21] zbog njihovih jasnih uvida u dvostruki način sorpcije i plinskih mješavina.

Mapiranje parametara

Sastavljam nazive parametara kako bih izbjegao zabunu. Radi jasnoće, ostajem pri (k), (C_H') i (b). Jednadžbe za čisti plin i smjesu detaljno su i jasno formatirane.

Rješavanje izazova

Bavim se prilagođavanjem parametara višestrukih rješenja, plastifikacijom polimera i vremenskim efektima. Ove zamršenosti čine predviđanje sorpcije čistih i miješanih plinova složenim.

Sastavljanje

Slažem dijelove o razlikama u sorpciji, modelu s dvorežimskim načinom rada za čiste plinove, njegovoj primjeni na mješavine plinova i s time povezanim izazovima. Taj se napredak čini logičnim i učinkovitim.

Stopa prolaznosti na zadacima na ekspertnoj razini prema procijenjenoj ekonomskoj vrijednosti
Stopa prolazaProcijenjena ekonomska vrijednost
Stopa prolaza na zadacima stručne razine prema procijenjenim satima
Stopa prolazaProcijenjeno vrijeme
Procijenjena ekonomska vrijednost zadatka više je povezana sa stopom prolaza nego s brojem sati koji bi bili potrebni čovjeku – ono što modeli smatraju teškim razlikuje se od onoga što ljudi smatraju dugotrajnim.

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.

Što je sljedeće

Dubinsko istraživanje dostupno je već danas na web-stranici ChatGPT‑a, a bit će uvedeno u mobilne i desktop aplikacije unutar mjesec dana. Trenutačno, dubinsko istraživanje može pristupiti otvorenom webu i bilo kojim prenesenim datotekama. U budućnosti ćete se moći povezati s više specijaliziranim izvorima podataka – proširujući pristup resursima temeljenim na pretplati ili internim resursima – kako biste njegov izlaz učinili još robusnijim i personaliziranijim.

Gledajući dalje u budućnost, predviđamo da će se iskustva izvršitelja spojiti u ChatGPT‑u za asinkrono istraživanje i izvršavanje u stvarnom svijetu. Kombinacija dubinskog istraživanja, koje može provoditi asinkrono internetsko istraživanje, i Operatora, koji može poduzimati stvarne radnje, omogućit će ChatGPT‑u da za vas obavlja sve složenije zadatke.

Dodatak od 3. veljače 2025.: Proveli smo rigorozna sigurnosna testiranja, procjene spremnosti i preglede upravljanja za ranu verziju modela o3 koja omogućuje dubinsko istraživanje, pri čemu je ta verzija ocijenjena kao srednji⁠(otvara se u novom prozoru) rizik. Također smo proveli dodatna sigurnosna testiranja kako bismo bolje razumjeli dodatne rizike povezane s mogućnošću dubinskog istraživanja da pregledava web, i uveli smo nove zaštitne mjere. Nastavit ćemo temeljito testirati i pomno nadzirati trenutačno ograničeno izdanje. Svoja sigurnosna saznanja i zaštitne mjere za dubinsko istraživanje podijelit ćemo u dokumentu o sustavu kad proširimo pristup korisnicima paketa 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 i Zhiqing Sun

Foundational Contributors

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