Zum Hauptinhalt springen
OpenAI

2. Februar 2025

Veröffentlichung

Eine Einführung in Deep Research

Ein Agent, der mithilfe von Reasoning große Mengen an Online-Informationen synthetisiert und mehrstufige Rechercheaufgaben für dich ausführt. Schon heute für Pro-Benutzer verfügbar, bald auch für Plus und Team.

Laden …

Update vom 10. Februar 2026: Du kannst Deep Research jetzt mit jedem MCP oder jeder App verbinden und Websuchen auf vertrauenswürdige Websites beschränken, damit du dich auf authentifizierte, branchenübliche Quellen konzentrieren kannst. Du kannst außerdem den Fortschritt in Echtzeit verfolgen und mit Folge-Prompts oder neuen Quellen unterbrechen und verfeinern. Wir haben die visuelle Darstellung aktualisiert, damit du deine Recherche einfacher starten, verfolgen und von Anfang bis Ende prüfen kannst.


Update vom 17. Juli 2025: Deep Research kann jetzt noch tiefer und breiter recherchieren – mit Zugriff auf einen visuellen Browser als Teil des ChatGPT‑Agenten. Um diese aktualisierten Funktionen zu nutzen, wähle einfach „Agent-Modus“ im Dropdown-Menü im Eingabefeld aus und gib deine Anfrage direkt ein. Die ursprüngliche Deep-Research-Funktion bleibt über die Option „Deep Research“ im Tools-Menü verfügbar.


Update vom 24. April 2025: Wir erhöhen die Nutzungsquoten Deep Research – 25 Anfragen pro Monat für Plus, Team, Enterprise und Edu, 250 für Pro und 5 für Free. Möglich wird das durch eine neue leichtere Version von Deep Research, unterstützt durch eine Version von o4-mini, die kosteneffizienter ist und zugleich hohe Qualität bietet. Sobald du dein Limit für die Vollversion erreichst, wechseln deine Anfragen automatisch zur leichteren Version.


Update vom 25. Februar 2025: Alle Plus-Nutzer:innen können Deep Research jetzt nutzen.


Update vom 5. Februar 2025: Deep Research ist jetzt für Pro-Nutzer:innen im Vereinigten Königreich, in der Schweiz und im Europäischen Wirtschaftsraum verfügbar.


Heute starten wir mit Deep Research in ChatGPT, einer neuen Agentenfunktion, die mehrstufige Recherchen im Internet für komplexe Aufgaben durchführt. In Minuten werden Ergebnisse erzielt, für die ein Mensch viele Stunden brauchen würde.

Deep Research ist der nächste Agent von OpenAI, der selbstständig für dich arbeiten kann. Auf deinen Prompt hin findet, analysiert und synthetisiert ChatGPT Hunderte von Online-Quellen, um einen umfassenden Bericht auf Forschungsanalyseniveau zu erstellen. Unterstützt von einer Version des anstehenden OpenAI o3‑Modells, das für die Onlinesuche und Datenanalyse optimiert ist, werden mithilfe von Reasoning riesige Mengen an Text, Bildern und PDFs im Internet durchsucht, interpretiert und analysiert und die gefundenen Informationen nach Bedarf angepasst.

Die Fähigkeit, Wissen zu synthetisieren ist eine Voraussetzung, um neues Wissen zu schaffen. Aus diesem Grund ist Deep Research ein wichtiger Schritt auf dem Weg zu unserem übergeordneten Ziel, eine AGI zu entwickeln, von der wir schon lange glauben, dass sie in der Lage ist, neuartige wissenschaftliche Erkenntnisse zu liefern.

Unsere Motivation hinter der Entwicklung von Deep Research

Deep Research ist für Menschen konzipiert, die intensive Wissensarbeit in Bereichen wie Finanzen, Wissenschaft, Politik und Technik leisten und einen gründlichen, präzisen und verlässlichen Rechercheansatz benötigen. Auch anspruchsvolle Käufer, die nach hyperpersonalisierten Empfehlungen suchen, welche üblicherweise eine sorgfältige Recherche erfordern, wie für Autos, Haushaltsgeräte und Möbel, können stark davon profitieren. Jeder Output ist vollständig dokumentiert, mit klaren Quellenangaben und einer Zusammenfassung der Denkschritte, sodass die Angaben leicht zitiert und verifiziert werden können. Gerade für die Suche nach Nischeninformationen, die nicht intuitiv zu finden sind und für die das Durchsuchen zahlreicher Websites erforderlich wäre, kann Deep Research besonders wertvoll sein. Mit Deep Research gewinnst du wertvolle Zeit, da du komplexe, zeitintensive Web-Recherchen mit einer einzigen Abfrage auslagern und beschleunigen kannst.

Deep Research kann Erkenntnisse aus dem gesamten Internet unabhängig aufdecken, analysieren und konsolidieren. Um dies zu erreichen, wurde es anhand praxisbezogener Aufgaben trainiert, die die Verwendung von Browsern und Python-Tools erfordern. Dabei kamen dieselben Reinforcement Learning-Methoden zum Einsatz, die auch als Grundlage für OpenAI o1, unserem ersten schlussfolgernden Modell, dienen. Während o1 eindrucksvolle Fähigkeiten in den Bereichen Programmieren, Mathematik und anderen technischen Gebieten demonstriert, erfordern viele Herausforderungen aus der Praxis umfangreiche Kontext- und Informationsbeschaffung aus verschiedenen Online-Quellen. Deep Research baut auf diesen Reasoning-Fähigkeiten auf, um die Lücke zu schließen und die Probleme anzugehen, mit denen Menschen im Berufs- und Alltagsleben konfrontiert sind.

So funktioniert Deep Research

Wähle im Nachrichtenfeld von ChatGPT „Deep Research“ aus und gib deine Anfrage ein. Teile ChatGPT mit, was du brauchst – ob es sich um eine Wettbewerbsanalyse auf Streaming-Plattformen oder einen personalisierten Bericht zum besten Fahrrad für Pendler handelt. Du kannst Dateien oder Arbeitsblätter anhängen, um deine Frage mit mehr Kontext zu versehen. Sobald die Recherche läuft, erscheint eine Seitenleiste mit einer Übersicht über die durchgeführten Schritte und verwendeten Quellen.

Deep Research benötigt etwa 5 bis 30 Minuten für eine tiefgehende Recherche im Internet. In der Zwischenzeit kannst du dich zurücklehnen oder an etwas anderem arbeiten – sobald die Recherche abgeschlossen ist, wirst du benachrichtigt. Der endgültige Output erfolgt als Bericht im Chat. In den nächsten Wochen werden wir außerdem eingebettete Bilder, Datenvisualisierungen und andere analytische Outputs zu diesen Berichten hinzufügen, um zusätzliche Klarheit und Kontext zur Verfügung zu stellen.

Im Vergleich zu Deep Research ist GPT‑4o ideal für multimodale Gespräche in Echtzeit. Bei vielschichtigen, Domain-spezifischen Anfragen, bei denen Tiefe und Detail entscheidend sind, macht die Fähigkeit von Deep Research, umfassende Untersuchungen anzustellen und jede Behauptung zu belegen, den Unterschied zwischen einem schnellen Überblick und einer gut dokumentierten, überprüften Antwort aus, die als Arbeitsprodukt verwendet werden kann.

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 geht äußerst detailliert auf den Prompt ein und stellt länderspezifische Daten sowohl für die Top 10 Industrieländer als auch für die Top 10 Entwicklungsländer nebeneinander bereit, um eine einfache Bezugnahme und einen problemlosen Vergleich zu ermöglichen. Es nutzt diese Informationen, um detaillierte, fundierte und brauchbare Empfehlungen für den Markteintritt zu liefern.

Funktionsweise

Deep Research wurde mithilfe von umfassendem Reinforcement Learning an anspruchsvollen Such- und Reasoning-Aufgaben in einer Reihe von Domains trainiert. Anhand dieses Training lernte es, eine mehrstufige Verlaufskurve zu planen und auszuführen, um die benötigten Daten zu finden, gegebenenfalls zurückzuverfolgen und auf Echtzeitinformationen zu reagieren. Das Modell kann zudem von Benutzern hochgeladene Dateien durchsuchen, mithilfe des Python-Tools Diagramme zeichnen und iterieren, generierte Diagramme und Bilder von Websites in seine Antworten einbetten und bestimmte Sätze oder Textstellen aus seinen Quellen zitieren. Infolge dieses Trainings erreicht es bei zahlreichen öffentlichen Bewertungen mit Schwerpunkt auf praxisbezogenen Problemen neue Höchstwerte.

Humanity's Last Exam

Auf Humanity’s Last Exam(wird in einem neuen Fenster geöffnet), einer kürzlich veröffentlichten Bewertung, die KI anhand von Fragen auf Experten-Level zu einem breiten Themenspektrum testet, erreicht das Modell, auf das sich Deep Research stützt, mit 26,6 % Genauigkeit einen neuen Höchstwert. Dieser Test besteht aus über 3.000 Multiple-Choice- und Kurzantwortfragen zu über 100 Themen von Linguistik über Raketentechnik und Klassik bis Ökologie. Im Vergleich zu OpenAI o1 konnten die größten Erfolge auf den Gebieten Chemie, Geistes- und Sozialwissenschaften sowie Mathematik verzeichnet werden. Das Modell, auf dem Deep Research basiert, demonstriert einen menschenähnlichen Ansatz, indem es bei Bedarf effektiv nach Fachinformationen sucht.

ModellGenauigkeit (%)
GPT-4o3,3
Grok-23,8
Claude 3.5 Sonett4,3
Gemini Thinking6,2
OpenAI o19,1
DeepSeek-R1*9,4
OpenAI o3-mini (mittel)*10,5
OpenAI o3-mini (hoch)*13,0
OpenAI Deep Research**26,6
* Modell ist nicht multimodal, bewertet wurde nur der Text-Teil.
**mit Browsing- und Python-Tools

GAIA

Auf GAIA(wird in einem neuen Fenster geöffnet)1,, einer öffentlichen Benchmark, die KI anhand realer Fragen bewertet, erreicht das auf Deep Research basierte Modell einen neuen Stand der Technik (SOTA) und führt die externe Bestenliste(wird in einem neuen Fenster geöffnet) an. Die Aufgaben umfassen Fragen in drei Schwierigkeitsstufen. Für einen erfolgreichen Abschluss sind unter anderem Fähigkeiten wie Reasoning, multimodale Sprachkompetenz, Onlinesuche und der sichere Umgang mit Tools erforderlich.

GAIA
Level 1Level 2Level 3Durchschnitt.
Vorherige SOTA(wird in einem neuen Fenster geöffnet)67,9267,4442,3163,64
Deep Research (pass@1)74,2969,0647,667,36
Deep Research (cons@64)78,6673,2158,0372,57

GAIA Beispielaufgaben

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]

Aufgaben auf Experten-Level

Bei einer internen Bewertung von Aufgaben auf Experten-Level in verschiedenen Bereichen kamen Fachexperten zu dem Schluss, dass Deep Research mehrere Stunden langwieriger, manueller Nachforschungen automatisieren konnte. 

Erfolgsquote vs. maximale Tool-Aufrufe
ErfolgsquoteMaximale Tool-Aufrufe
Je mehr das Modell durchsucht und über das nachdenkt, was es durchsucht, desto besser ist seine Leistung. Deshalb ist es wichtig, ihm Zeit zum Denken zu geben.
Beispiele für Experten-Level
Eingesparte Zeit für Aufgaben: 4 Stunden

I am a researcher interested in bringing mixed-gas sorption capabilities to my lab. Please discuss the differences between pure- and mixed-gas sorption for glassy polymers, how the dual-mode sorption model can be used to predict mixed-gas sorption behavior in glassy polymers (include equations where applicable), and what challenges there are in accurately predicting pure- and mixed-gas sorption using the dual-mode sorption model. Only include open-source information as of October 1, 2024.

Pure vs. mixed-gas sorption in glassy polymers: In a glassy polymer (below TgT_g), a single gas typically exhibits a concave sorption isotherm: uptake rises sublinearly with pressure, unlike the linear Henry’s-law behavior above TgT_g. This is attributed to “dual-mode” sorption: some penetrant dissolves in the dense polymer matrix (obeying Henry’s law) while additional penetrant saturates specific microvoid “sites” (a Langmuir-type adsorption in the polymer’s nonequilibrium free volume). By contrast, when two or more gases are present, they compete for those limited Langmuir sorption sites. As a result, each component’s sorbed concentration in a mixture is generally lower than it would be at the same partial pressure alone. In particular the less soluble (lower-affinity) gas tends to be more strongly suppressed, often causing the mixed-gas solubility selectivity (ratio of concentrations) to exceed the ideal value predicted from pure-gas isotherms. For example, in CO₂/CH₄ mixtures both components sorb less than in their pure-gas cases (especially CH₄), so the CO₂/CH₄ sorption selectivity is higher under mixture conditions. In extreme cases, mixed-gas effects can even reverse performance trends observed with single gases. (We note that unlike competitive sorption, synergistic sorption – where one gas increases the sorption of another via polymer swelling – is usually minor in rigid high-free-volume polymers under moderate pressures.)

Dual-mode sorption model and mixed-gas prediction: The dual-mode sorption (DMS) model quantitatively captures glassy polymer sorption by superposing a Henry’s-law term and a Langmuir term. For a single gas, the sorbed concentration CC (e.g. in cm³(STP) gas per cm³ polymer) is written as:

C(p)=kDp  +  CHbp1+bp.C(p) = k_D\,p \;+\; \frac{C'_H\,b\,p}{\,1 + b\,p\,}\,.

Here kDk_D is the Henry’s law coefficient for dissolution, CHC'_H is the Langmuir capacity constant (proportional to the polymer’s unrelaxed free-volume or “hole” capacity), and bb is the Langmuir affinity constant. This empirical formula yields the characteristic concave isotherm of glassy polymers and reduces to simple Henry’s law at the glass-transition (since CH0C'_H \to 0 as TTgT \to T_g). The same three parameters (kD,CH,bk_D, C'_H, b) are obtained by fitting pure-gas sorption data and are then used to predict mixture sorption. For a binary mixture of gases A and B (with partial pressures pA,pBp_A, p_B), the DMS model assumes each gas obeys its own Henry’s term and that both compete for the same Langmuir sites. One convenient form is to write the total sorbed concentration as the sum of contributions from each gas:

Ctot=kD,ApA+kD,BpB  +  CH,AbApA  +  CH,BbBpB1+bApA+bBpB,C_{\text{tot}} = k_{D,A}p_A + k_{D,B}p_B \;+\; \frac{\,C'_{H,A}\,b_A\,p_A \;+\; C'_{H,B}\,b_B\,p_B\,}{\,1 + b_A p_A + b_B p_B\,}\,,

which implicitly means the concentration of component i in the mixture is Ci=kD,ipi+CH,ibipi1+jbjpjC_i = k_{D,i} p_i + \frac{C'_{H,i} b_i p_i}{\,1+\sum_j b_j p_j\,}. This reduces to the single-gas formula when the other component’s pressure is zero. In practice, partial pressure in these equations is often replaced by fugacity for accuracy at high pressures, though using fugacities or pressures gives nearly the same results if applied consistently. The DMS mixed-gas model predicts the competitive sorption effect observed experimentally – namely, each gas’s uptake is depressed relative to its pure-gas sorption isotherm.

Challenges and limitations: Although the dual-mode model is widely successful in correlating sorption data, it has notable limitations in predicting sorption behavior. First, the DMS model is empirical – its fitted parameters are not universal constants but can vary with polymer formation history, physical aging, and temperature/pressure range. This means a parameter set obtained under one set of conditions may lack predictive power outside its calibration range. For instance, sorption isotherms measured only over a limited pressure range can be fit well by DMS, but extrapolating beyond that (especially approaching plasticization pressures) may be unreliable. Indeed, multiple distinct combinations of kDk_D, CHC'_H, bb can sometimes fit the same pure-gas isotherm almost equally well – yet they yield markedly different mixed-gas predictions. This sensitivity undermines confidence in mixture forecasts, as one study showed that using different pure-gas fit sets led to only qualitative agreement with some mixed-CO₂/CH₄ data.

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

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

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]

[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]

[browse action]

[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.

Erfolgsquote bei Aufgaben auf Expertenniveau nach geschätztem wirtschaftlichen Wert
ErfolgsquoteGeschätzter wirtschaftlicher Wert
Erfolgsquote bei Aufgaben auf Expertenniveau nach geschätzten Stunden
ErfolgsquoteGeschätzte Stunden
Der geschätzte wirtschaftliche Wert einer Aufgabe korreliert eher mit der Erfolgsquote als mit der Anzahl der Stunden, die ein Mensch dafür benötigen würde – die Dinge, die Modelle als schwierig empfinden, unterscheiden sich von denen, die Menschen als zeitaufwändig empfinden.

Einschränkungen

Deep Research erschließt bedeutende neue Funktionen, aber es steckt noch in den Kinderschuhen und stößt auf Anwendungsgrenzen. Es kann zuweilen Fakten in Antworten halluzinieren oder falsche Schlussfolgerungen ziehen. Dies geschieht allerdings internen Auswertungen zufolge deutlich seltener als bei bestehenden ChatGPT‑Modellen. Manchmal kann es zuverlässige Informationen nicht von Gerüchten unterscheiden. Zudem weist es derzeit Schwächen bei der Vertrauenskalibrierung auf, sodass Unsicherheiten häufig nicht präzise wiedergegeben werden können. Beim Start können kleinere Formatierungsfehler in Berichten und Quellenangaben auftreten und es kann länger dauern, bis die Aufgaben ausgeführt werden. Wir gehen davon aus, dass sich Probleme dieser Art im Laufe der Zeit und mit zunehmender Nutzung schnell verbessern werden.

Zugriff

Die eingehende Recherche in ChatGPT ist derzeit äußerst rechenintensiv. Je länger die Recherche zur Antwort auf eine Anfrage dauert, desto mehr Inferenzberechnungen sind notwendig. Wir führen heute eine für Pro-Nutzer optimierte Version mit bis zu 100 Anfragen pro Monat ein. Plus- und Team-Benutzer erhalten als nächstes Zugriff, gefolgt von Enterprise. Wir arbeiten noch am Zugriff für Benutzer im Vereinigten Königreich, in der Schweiz und im Europäischen Wirtschaftsraum. 

Alle zahlenden Benutzer erhalten bald deutlich höhere Ratenlimits, wenn wir eine schnellere, kostengünstigere Version von Deep Research veröffentlichen, die auf einem kleineren Modell basiert, welches weiterhin qualitativ hochwertige Ergebnisse liefert. 

In den kommenden Wochen und Monaten werden wir an der technischen Infrastruktur arbeiten, die aktuelle Version genau überwachen und noch strengere Tests durchführen. Dies deckt sich mit unserem Prinzip der iterativen Bereitstellung. Wenn alle Sicherheitsprüfungen weiterhin unseren Veröffentlichungsstandards entsprechen, gehen wir davon aus, dass wir Deep Research unseren Plus-Benutzern in etwa einem Monat zur Verfügung stellen können.

So geht es weiter

Deep Research ist heute auf der ChatGPT‑Website verfügbar und wird im Laufe des Monats für Mobil- und Desktop-Anwendungen bereitgestellt. Derzeit kann Deep Research auf das offene Web und alle hochgeladenen Dateien zugreifen. In Zukunft wird eine Verbindung zu spezialisierteren Datenquellen möglich sein. Dadurch wird der Zugriff auf abonnementbasierte oder interne Ressourcen erweitert, um den Output noch robuster und individueller zu gestalten.

Unsere Vision für die weitere Zukunft ist es, agentische Erlebnisse in ChatGPT für asynchrone, reale Forschung und Ausführung zusammenzuführen. Die Kombination aus Deep Research, die asynchrone Online-Recherchen durchführen kann, und Operator, der in der Praxis Maßnahmen ergreifen kann, ermöglicht es ChatGPT, immer anspruchsvollere Aufgaben für dich zu übernehmen.


Nachtrag vom 3. Februar 2025: Wir haben strenge Sicherheitstests, Bewertungen der Einsatzbereitschaft sowie Governance-Prüfungen an der frühen Version von o3 durchgeführt, die als Grundlage für Deep Research dient, und das Risiko als mittel(wird in einem neuen Fenster geöffnet) eingestuft. Weitere Sicherheitstests wurden zudem durchgeführt, um die zusätzlichen Risiken im Zusammenhang mit der Fähigkeit von Deep Research, das Internet zu durchsuchen, besser zu verstehen, und wir haben neue Maßnahmen zur Risikominderung hinzugefügt. Wir werden die aktuelle eingeschränkte Version weiterhin ausführlich testen und genau überwachen. Unsere Sicherheitserkenntnisse und Schutzmaßnahmen im Bezug auf Deep Research werden wir in einer Systemkarte teilen, wenn wir den Zugriff auf Plus-Benutzer ausweiten.

Fußnoten

  1. 1

    Wir haben festgestellt, dass die Antworten auf die Ground-Truth-Fragen zu diesem Datensatz online in großem Umfang durchgesickert sind, und haben daher mehrere Websites bzw. URLs blockiert, um eine faire Bewertung des Modells sicherzustellen.

Autoren

OpenAI

Forschungsleitung

Isa Fulford und Zhiqing Sun

Beitragende der Stiftung

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

Hauptbeitragende

Forschung

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

Bereitstellung

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

Beitragende

Forschung

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

+ alle Mitwirkenden hinter o3.

Sicherheitssysteme

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

Bereitstellung

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

Geschäftsleitung

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