2 febbraio 2025

Ti presentiamo Deep Research

Un agente che utilizza il ragionamento per sintetizzare grandi quantità di informazioni online e completare per te attività di ricerca articolate in più passaggi. Disponibile da oggi per gli utenti Pro, a seguire per gli utenti Plus e Team.

Prova su ChatGPT

Caricamento in corso...

Aggiornamento del 10 febbraio 2026: ora puoi collegare la deep research a qualsiasi MCP o app e limitare le ricerche sul web a siti affidabili, così puoi concentrarti su fonti autenticate e conformi agli standard del settore. Ora puoi anche monitorare i progressi in tempo reale e interrompere la ricerca per perfezionarla con prompt di follow-up o nuove fonti. Abbiamo aggiornato l'esperienza visiva in modo che sia più facile avviare, monitorare e rivedere la tua ricerca dall'inizio alla fine.

Aggiornamento del 17 luglio 2025: Deep Research può ora effettuare ricerche ancora più approfondite e ampie grazie all'accesso a un browser visivo integrato nell'agente ChatGPT. Per accedere a queste funzionalità aggiornate, seleziona "modalità agente" dal menu a tendina nel compositore e inserisci direttamente la tua query. La funzionalità originale di Deep Research rimane disponibile tramite l'opzione "Deep Research" nel menu degli strumenti.

Aggiornamento del 24 aprile 2025: stiamo aumentando in modo significativo la frequenza con cui è possibile utilizzare la deep research: inoltre, gli utenti Plus, Team, Enterprise ed Edu ora hanno a disposizione 25 query al mese, gli utenti Pro ne hanno 250, mentre gli utenti Free 5. Questo è reso possibile grazie a una nuova versione leggera di deep research basata su una versione di o4-mini, progettata per essere più efficiente in termini di costi pur mantenendo un'elevata qualità. Una volta raggiunto il limite consentito per la versione completa, le query passeranno automaticamente alla versione leggera.

Aggiornamento del 25 febbraio 2025: tutti gli utenti Plus possono ora utilizzare Deep research.

Aggiornamento del 5 febbraio 2025: Deep Research è ora disponibile per gli utenti Pro nel Regno Unito, in Svizzera e nello Spazio economico europeo.

Oggi presentiamo Deep Research in ChatGPT, una nuova funzionalità agentica che conduce ricerche articolate in più passaggi su Internet per attività complesse. Nel giro di decine di minuti è in grado di svolgere ciò che a un essere umano richiederebbe molte ore.

Deep Research è il nuovo agente di OpenAI che lavora per te in autonomia: tu fornisci un prompt e ChatGPT trova, analizza e sintetizza centinaia di fonti online per creare un report completo, con la qualità di un research analyst. Basato su una versione del futuro modello OpenAI o3 ottimizzato per la navigazione su web e l’analisi dei dati, Deep Research sfrutta il ragionamento per cercare, interpretare e analizzare grandi quantità di testi, immagini e PDF online, adattando il suo approccio in base alle informazioni che trova.

La capacità di sintetizzare le informazioni è un prerequisito fondamentale per generarne delle nuove. È in quest’ottica che Deep Research rappresenta un importante passo in avanti verso il nostro obiettivo più ampio di sviluppare un'AGI in grado di contribuire attivamente alla ricerca scientifica.

Perché abbiamo sviluppato Deep Research

Deep Research è pensato per chi svolge lavori ad alta intensità cognitiva in ambiti come finanza, scienza, politica pubblica e ingegneria e necessita quindi di ricerche dettagliate, precise e affidabili. È altrettanto utile per i consumatori più attenti in cerca di consigli d’acquisto altamente personalizzati su prodotti che richiedono una valutazione approfondita, come auto, elettrodomestici e mobili. Ogni output include una documentazione dettagliata, fonti chiare e un riepilogo del processo di ragionamento, il che garantisce trasparenza e una facile consultazione dei dati. È particolarmente efficace nel trovare informazioni di nicchia e difficili da reperire che altrimenti richiederebbero la consultazione di molti siti web. Con Deep Research puoi risparmiare tempo prezioso velocizzando ricerche web lunghe e complesse con un'unica query.

Deep Research scopre, analizza e raggruppa autonomamente informazioni provenienti da tutto il web. A tal fine, è stato addestrato su attività reali che prevedono l’utilizzo di browser e Python, mediante le stesse tecniche di apprendimento per rinforzo del nostro primo modello di ragionamento, OpenAI o1. Sebbene o1 dimostri notevoli capacità di codifica, matematica e altri ambiti tecnici, molte sfide reali richiedono un contesto più ampio e la raccolta di informazioni da varie fonti online. Deep Research sfrutta queste capacità di ragionamento per colmare il divario e affrontare i problemi tipici del lavoro e della vita di tutti i giorni.

Come utilizzare Deep Research

In ChatGPT, seleziona "Deep Research" nel compositore di messaggi e inserisci la tua query. Basta dire a ChatGPT di cosa hai bisogno, che si tratti di un confronto tra piattaforme di streaming o di un report personalizzato sulla migliore bici per gli spostamenti quotidiani. Puoi allegare file o fogli elettronici per aggiungere più contesto alla tua domanda. All’avvio, si apre una barra laterale che mostra il riepilogo dei passaggi eseguiti e delle fonti utilizzate.

Deep Research può impiegare dai 5 ai 30 minuti per completare il suo lavoro, il tempo necessario per effettuare una ricerca approfondita sul web. Nel frattempo, puoi allontanarti e dedicarti ad altre attività: una notifica ti avviserà al termine della ricerca. Il risultato finale viene fornito sotto forma di report nella chat. Nelle prossime settimane aggiungeremo anche immagini, visualizzazioni di dati e altri output analitici per rendere il tutto ancora più chiaro e contestualizzato.

Rispetto a Deep Research, GPT‑4o è ideale per conversazioni multimodali in tempo reale. Per richieste complesse e specifiche di settore dove profondità e dettagli sono fondamentali, invece, Deep Research si distingue per le sue analisi approfondite e citazioni puntuali che trasformano un rapido riassunto in una risposta ben documentata, verificata e affidabile.

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:

United States
Japan
Germany
United Kingdom
France
Italy
Canada
South Korea
Australia
Spain

Top 10 Developing Countries by GDP:

China
India
Brazil
Russia
Indonesia
Mexico
Turkey
Saudi Arabia
Argentina
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

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 risponde al prompt in modo estremamente dettagliato e offre dati affiancati per i primi 10 Paesi sviluppati e i primi 10 Paesi in via di sviluppo, facilitando così la consultazione e il confronto. Sfrutta queste informazioni per offrire consigli di ingresso nel mercato dettagliati, affidabili e concreti.

Come funziona

Deep Research è stato addestrato con tecniche di apprendimento per rinforzo end-to-end su complesse attività di navigazione e ragionamento in vari ambiti. Grazie a questo tipo di addestramento, ha imparato a pianificare ed eseguire una strategia in più passaggi per trovare i dati di cui ha bisogno ed è in grado di adattarsi alle informazioni in tempo reale quando necessario. Il modello è anche in grado di esaminare i file caricati dagli utenti, creare e modificare grafici mediante Python, incorporare sia grafici generati che immagini provenienti da siti web nelle sue risposte, e citare frasi o passaggi specifici dalle fonti consultate. Questo addestramento garantisce prestazioni mai raggiunte prima in numerosi benchmark pubblici dedicati a problemi reali.

Humanity's Last Exam

In Humanity’s Last Exam⁠(si apre in una nuova finestra), una nuova valutazione che misura le prestazioni dell'IA su domande complesse in numerosi ambiti, il modello alla base di Deep Research ha raggiunto un nuovo record di precisione del 26,6%. Questo test comprende oltre 3.000 domande a scelta multipla e a risposta breve su più di 100 discipline, dalla linguistica all’ingegneria aerospaziale, dai classici all’ecologia. Rispetto a OpenAI o1, i miglioramenti più notevoli sono emersi in ambiti come chimica, scienze umane e sociali e matematica. Il modello alla base di Deep Research ha mostrato un approccio simile a quello umano, cercando efficacemente informazioni specialistiche quando necessario.

Modello	Precisione (%)
GPT-4o	3,3
Grok-2	3,8
Claude 3.5 Sonnet	4,3
Pensiero di Gemini	6,2
OpenAI o1	9,1
DeepSeek-R1*	9,4
OpenAI o3-mini (medio)*	10,5
OpenAI o3-mini (alto)*	13,0
Deep Research di OpenAI	26,6

* Il modello non è multimodale, valutato solo su un sottoinsieme di testo.

**con navigazione + strumenti python

GAIA

In GAIA⁠(si apre in una nuova finestra)¹, un benchmark pubblico che valuta l'IA su domande legate al mondo reale, il modello di Deep Research stabilisce un nuovo stato dell'arte (SOTA) e si posiziona al primo posto della classifica⁠(si apre in una nuova finestra) esterna. Per affrontare con successo domande di tre livelli di difficoltà, sono necessarie abilità di ragionamento, padronanza multimodale, navigazione su web e utilizzo di strumenti.

GAIA
	Livello 1	Livello 2	Livello 3	Media
SOTA precedente(si apre in una nuova finestra)	67,92	67,44	42,31	63,64
Deep Research (pass@1)	74,29	69,06	47,6	67,36
Deep Research (cons@64)	78,66	73,21	58,03	72,57

Esempi di attività in 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.

[search action]

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.

[browse action]

Reflecting on potential issues

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

[browse action]

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.

[search action]

Pinpointing key features

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

[browse action]

Piecing together insights

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

[search action]

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.

[search action]

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.

[search action]

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.

[browse action]

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.

[browse action]

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."

[browse action]

Evaluating library sources

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

[browse action]

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.

[browse action]

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.

[browse action]

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.

[browse action]

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.

[search action]

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.

[search action]

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.

[search action]

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.

[search action]

Attività di livello avanzato

In una valutazione interna su attività di livello avanzato in vari ambiti, secondo alcuni esperti di settore Deep Research è stato in grado di automatizzare numerose ore di complesse ricerche manuali.

Confronto tra tasso di superamento e chiamate strumento massime

Maggiore è il tempo che il modello dedica alla navigazione e alla riflessione, migliori sono le prestazioni: per questo è fondamentale lasciargli il tempo di pensare.

Esempi di attività di livello avanzato

Tempo risparmiato su questa attività: 4 ore

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 $T_g$ ), a single gas typically exhibits a concave sorption isotherm: uptake rises sublinearly with pressure, unlike the linear Henry’s-law behavior above $T_g$ . 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 $C$ (e.g. in cm³(STP) gas per cm³ polymer) is written as:

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

Here $k_D$ is the Henry’s law coefficient for dissolution, $C'_H$ is the Langmuir capacity constant (proportional to the polymer’s unrelaxed free-volume or “hole” capacity), and $b$ 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 $C'_H \to 0$ as $T \to T_g$ ). The same three parameters ( $k_D, C'_H, b$ ) 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 $p_A, p_B$ ), 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:

$C_{\text{tot}} = k_{D,A}p_A + k_{D,B}p_B \;+\; \frac{\,C'_{H,A}\,b_A\,p_A \;+\; C'_{H,B}\,b_B\,p_B\,}{\,1 + b_A p_A + b_B p_B\,}\,,$

which implicitly means the concentration of component i in the mixture is $C_i = k_{D,i} p_i + \frac{C'_{H,i} b_i p_i}{\,1+\sum_j b_j p_j\,}$ . 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 $k_D$ , $C'_H$ , $b$ can sometimes fit the same pure-gas isotherm almost equally well – yet they yield markedly different mixed-gas predictions. This sensitivity undermines confidence in mixture forecasts, as one study showed that using different pure-gas fit sets led to only qualitative agreement with some mixed-CO₂/CH₄ data.

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

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

Understanding sorption models

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

[search action]

Assessing open access

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

[browse action]

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

[browse action]

Clarifying key properties

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

[browse action]

Piecing together

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

[browse action]

Confirming title relevance

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

[search action]

Examining article connections

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

[browse action]

Gathering info

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

[search action]

Comparing gas sorption

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

[browse action]

Linking concepts

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

[search action]

Requesting review details

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

[browse action]

Checking PDF link

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

[search action]

Predicting sorption behavior

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

[browse action]

Fetching a PDF

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

[browse action]

Evaluating repository options

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

[search action]

Refining the focus

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

[search action]

Understanding sorption models

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

[search action]

Exploring hero.epa.gov

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

[browse action]

Refining the model

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

[browse action]

Addressing dual sorption model challenges

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

[browse action]

Quantifying deviation

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

[browse action]

Incorporating references

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

[browse action]

Proposing sections

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

Organizing content

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

[search action]

Choosing citations

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

Mapping out parameters

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

Addressing challenges

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

Piecing together

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

Tasso di superamento nelle attività di livello esperto in base al valore economico stimato

Tasso di superamento nelle attività di livello esperto in base alle ore stimate

Il valore economico stimato di un'attività è più correlato al tasso di superamento che al numero di ore necessarie a un essere umano: ciò che i modelli trovano difficile non coincide con ciò che richiede più tempo agli esseri umani.

Limiti

Deep Research introduce nuove importanti funzionalità, ma si trova ancora in una fase iniziale e presenta delle limitazioni. Può occasionalmente generare informazioni inesatte nelle risposte o trarre conclusioni errate, anche se con una frequenza notevolmente inferiore rispetto ai modelli di ChatGPT attuali, secondo valutazioni interne. Può avere difficoltà a distinguere tra informazioni autorevoli e semplici speculazioni e al momento presenta limiti nella calibrazione della sicurezza, spesso senza riuscire a comunicare correttamente il grado di incertezza. Al momento del rilascio, potrebbero verificarsi piccoli errori di formattazione nei report e nelle citazioni e l’avvio delle attività potrebbe richiedere più tempo del previsto. Riteniamo che questi aspetti miglioreranno rapidamente con l’uso e il passare del tempo.

Accesso

Al momento la funzione di Deep Research in ChatGPT richiede un’elevata potenza di calcolo. Più tempo è necessario per svolgere una ricerca, maggiore sarà la potenza di calcolo richiesta per l’inferenza. Iniziamo con una versione ottimizzata per gli utenti Pro, che permette fino a 100 query mensili. L'accesso sarà esteso successivamente agli utenti Plus e Team, seguiti da quelli Enterprise. Stiamo ancora lavorando per offrire l’accesso agli utenti nel Regno Unito, in Svizzera e nello Spazio economico europeo.

Presto, tutti gli utenti abbonati potranno beneficiare di limiti di utilizzo molto più alti grazie al rilascio di una versione più veloce ed economica di Deep Research, basata su un modello più piccolo ma ugualmente performante.

Nelle prossime settimane e mesi ci concentreremo sull’infrastruttura tecnica, monitoreremo attentamente la versione attuale e svolgeremo test ancora più rigorosi, in linea con il nostro approccio di implementazione iterativa. Se tutti i controlli di sicurezza continueranno a rispettare i nostri standard, prevediamo di rilasciare Deep Research agli utenti Plus entro circa un mese.

Novità

Deep Research è già disponibile su ChatGPT web e arriverà sulle app mobile e desktop entro la fine del mese. Attualmente Deep Research può accedere al web aperto e a tutti i file caricati. In futuro sarà possibile collegarsi a fonti di dati più specializzate, ampliando l’accesso a risorse in abbonamento o interne, al fine di rendere i risultati ancora più completi e personalizzati.

Nel lungo termine prevediamo che ChatGPT combini esperienze agentiche per supportare attività di ricerca ed esecuzione asincrone del mondo reale. Grazie all’integrazione tra Deep Research, che esegue ricerche online asincrone, e Operator, che compie azioni reali, ChatGPT sarà in grado di gestire per te attività sempre più sofisticate.

Nota aggiuntiva del 3 febbraio 2025: abbiamo effettuato test di sicurezza rigorosi, valutazioni della preparazione e revisioni della governance sulla prima versione di o3 alla base di Deep Research e abbiamo identificato un livello di rischio medio⁠(si apre in una nuova finestra). Abbiamo inoltre eseguito test di sicurezza aggiuntivi per comprendere meglio i rischi incrementali legati alla capacità di Deep Research di navigare sul web e abbiamo aggiunto nuove misure di mitigazione. Proseguiremo con test rigorosi e un attento monitoraggio dell'attuale versione limitata. Condivideremo le nostre analisi di sicurezza e le misure di protezione per Deep Research in una scheda di sistema quando estenderemo l’accesso agli utenti Plus.

Note di riferimento

1
Abbiamo scoperto che le risposte di verità di base per questo set di dati sono state ampiamente diffuse online e di conseguenza abbiamo bloccato diversi siti web o URL per garantire una valutazione equa del modello.

Autori

OpenAI

Responsabili della ricerca

Isa Fulford e Zhiqing Sun

Contributori fondamentali

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

Collaboratori principali

Ricerca

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

Distribuzione

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

Collaboratori

Ricerca

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

+ tutti i collaboratori di o3.

Sistemi di sicurezza

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

Distribuzione

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

Direttivo

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