Μετάβαση στο κύριο περιεχόμενο
OpenAI

2 Φεβρουαρίου 2025

Έκδοση

Παρουσίαση της έρευνας σε βάθος

Ένας πράκτορας που χρησιμοποιεί συλλογιστική για να συνθέτει μεγάλο όγκο διαδικτυακών πληροφοριών και να ολοκληρώνει ερευνητικές εργασίες πολλαπλών βημάτων για λογαριασμό σας. Διατίθεται σήμερα στους χρήστες Pro και ακολουθούν οι χρήστες Plus και Team.

Φόρτωση…

Ενημέρωση 10 Φεβρουαρίου 2026: Μπορείτε πλέον να συνδέσετε την έρευνα σε βάθος με οποιοδήποτε MCP ή εφαρμογή και να περιορίσετε τις αναζητήσεις στο web σε αξιόπιστους ιστότοπους, ώστε να εστιάζετε σε επαληθευμένες πηγές σύμφωνες με τα πρότυπα του εκάστοτε κλάδου. Μπορείτε επίσης πλέον να παρακολουθείτε την πρόοδο σε πραγματικό χρόνο και να διακόπτετε για να βελτιώνετε με διευκρινιστικές προτροπές ή νέες πηγές. Έχουμε ενημερώσει την οπτική εμπειρία ώστε να είναι πιο εύκολο να ξεκινήσετε, να παρακολουθείτε και να ελέγχετε την έρευνά σας από την αρχή μέχρι το τέλος.


Ενημέρωση 17 Ιουλίου 2025: Η έρευνα σε βάθος μπορεί πλέον να επεκταθεί ακόμη περισσότερο και να διευρυνθεί με πρόσβαση σε ένα οπτικό πρόγραμμα περιήγησης ως μέρος του πράκτορα ChatGPT. Για να αποκτήσετε πρόσβαση σε αυτές τις ενημερωμένες δυνατότητες, απλώς επιλέξτε «λειτουργία πράκτορα» από το αναπτυσσόμενο μενού στο εργαλείο σύνθεσης και εισαγάγετε απευθείας το ερώτημά σας. Η αρχική λειτουργικότητα της έρευνας σε βάθος παραμένει διαθέσιμη μέσω της επιλογής «έρευνα σε βάθος» στο μενού εργαλείων.


Ενημέρωση 24 Απριλίου 2025: Αυξάνουμε σημαντικά τη συχνότητα χρήσης της έρευνας σε βάθος—Επίσης, οι χρήστες Plus, Team, Enterprise και Edu λαμβάνουν πλέον 25 ερωτήματα ανά μήνα, οι χρήστες Pro λαμβάνουν 250 και οι χρήστες Free λαμβάνουν 5. Αυτό καθίσταται δυνατό μέσω μιας νέας ελαφριάς έκδοσης της έρευνας σε βάθος που υποστηρίζεται από μια έκδοση του o4-mini, σχεδιασμένη να είναι πιο οικονομική, διατηρώντας παράλληλα υψηλή ποιότητα. Μόλις φτάσετε το όριο για την πλήρη έκδοση, τα ερωτήματά σας θα μεταβαίνουν αυτόματα στην ελαφριά έκδοση.


Ενημέρωση 25 Φεβρουαρίου 2025: Όλοι οι χρήστες Plus μπορούν τώρα να χρησιμοποιούν έρευνα σε βάθος.


Ενημέρωση 5 Φεβρουαρίου 2025: Η έρευνα σε βάθος είναι πλέον διαθέσιμη σε χρήστες Pro στο Ηνωμένο Βασίλειο, την Ελβετία και τον Ευρωπαϊκό Οικονομικό Χώρο.


Σήμερα κυκλοφορούμε την έρευνα στο βάθος στο ChatGPT, μία νέα πρακτορική ικανότητα, η οποία πραγματοποιεί διαδικτυακή έρευνα πολλαπλών βημάτων για πολύπλοκες εργασίες. Καταφέρνει σε λίγα λεπτά αυτό για το οποίο ένας άνθρωπος θα χρειαζόταν πολλές ώρες.

Η έρευνα σε βάθος αποτελεί τον νέο πράκτορα του OpenAI που μπορεί να δουλέψει ανεξάρτητα για λογαριασμό σας. Απλώς του δίνετε μια προτροπή και το ChatGPT θα βρει, θα αναλύσει και θα συνθέσει εκατοντάδες διαδικτυακές πηγές για να συντάξει μία συνολική αναφορά σε επίπεδο ερευνητικού αναλυτή. Υποστηριζόμενο από μια έκδοση του επερχόμενου μοντέλου OpenAI o3 που είναι βελτιστοποιημένη για περιήγηση στο διαδίκτυο και ανάλυση δεδομένων, αξιοποιεί τη συλλογιστική για την αναζήτηση, την ερμηνεία και την ανάλυση τεράστιων ποσοτήτων κειμένου, εικόνων και PDF στο διαδίκτυο, προσαρμόζοντας το σύστημα σε συγκεκριμένες ανάγκες, ανάλογα με τις πληροφορίες που συναντά.

Η ικανότητα σύνθεσης γνώσης αποτελεί προϋπόθεση για τη δημιουργία νέας γνώσης. Για αυτόν τον λόγο, η έρευνα σε βάθος σηματοδοτεί ένα μεγάλο βήμα προς τον ευρύτερο στόχο μας για την ανάπτυξη της Γενικής Τεχνητής Νοημοσύνης (AGI), την οποία έχουμε οραματιστεί εδώ και καιρό ως ικανή να παράγει νέα επιστημονική έρευνα.

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.

Πώς λειτουργεί

Η έρευνα σε βάθος εκπαιδεύτηκε χρησιμοποιώντας ενισχυτική μάθηση από άκρο σε άκρο σε δύσκολες εργασίες περιήγησης και συλλογισμού σε μια σειρά τομέων. Μέσω αυτής της εκπαίδευσης, έμαθε να δημιουργεί και να εκτελεί ένα πρόγραμμα πολλαπλών βημάτων για να βρει τα δεδομένα που χρειάζεται, να παρακολουθεί και να αντιδρά σε πληροφορίες σε πραγματικό χρόνο όπου είναι απαραίτητο. Το μοντέλο είναι επίσης σε θέση να περιηγηθεί σε αρχεία που έχουν ανεβάσει οι χρήστες, να σχεδιάσει και να επαναλάβει γραφήματα χρησιμοποιώντας το εργαλείο python, να ενσωματώσει γραφήματα και εικόνες που δημιουργούνται από ιστότοπους στις απαντήσεις του και να αναφέρει συγκεκριμένες προτάσεις ή αποσπάσματα από τις πηγές του. Ως αποτέλεσμα αυτής της εκπαίδευσης, φτάνει σε νέα υψηλά επίπεδα σε μια σειρά δημόσιων αξιολογήσεων που επικεντρώνονται σε προβλήματα του πραγματικού κόσμου.

Humanity’s Last Exam

Στην πρόσφατη αξιολόγηση Humanity's Last Exam(ανοίγει σε νέο παράθυρο) που δοκιμάζει την Τεχνητή Νοημοσύνη σε ένα ευρύ φάσμα θεμάτων με ερωτήσεις σε επίπεδο ειδικού, το μοντέλο που υποστηρίζει την έρευνα σε βάθος σημείωσε νέα κορυφαία επίδοση καθώς είχε ακρίβεια 26,6%. Αυτή η δοκιμή περιλαμβάνει περισσότερες από 3.000 ερωτήσεις πολλαπλής επιλογής και σύντομης απάντησης, σε περισσότερα από 100 θέματα από τη γλωσσολογία έως την επιστήμη των πυραύλων και από την κλασική φιλολογία έως την οικολογία. Σε σύγκριση με το OpenAI o1, οι μεγαλύτερες βελτιώσεις εμφανίστηκαν στη χημεία, τις ανθρωπιστικές και κοινωνικές επιστήμες, καθώς και τα μαθηματικά. Το μοντέλο που υποστηρίζει την έρευνα σε βάθος παρουσίασε μια ανθρώπινη προσέγγιση αναζητώντας αποτελεσματικά εξειδικευμένες πληροφορίες όταν ήταν απαραίτητο.

ΜοντέλοΑκρίβεια (%)
GPT-43,3
Grok-23,8
Claude 3.5 Sonnet4,3
Σκέψη των Διδύμων6,2
OpenAI o19,1
DeepSeek-R1*9,4
OpenAI o3-mini (μεσαίο)*10,5
OpenAI o3-mini (υψηλό)*13,0
Έρευνα σε βάθος της OpenAI**26,6
* Το μοντέλο δεν είναι πολυτροπικό, αξιολογείται σε υποσύνολο που περιλαμβάνει μόνο κείμενο.
**με εργαλεία περιήγησης + εργαλεία python

GAIA

Στο GAIA(ανοίγει σε νέο παράθυρο)1, ένα δημόσιο σημείο αναφοράς που αξιολογεί την ΤΝ σε ερωτήματα πραγματικού κόσμου, το μοντέλο που υποστηρίζει την έρευνα σε βάθος φτάνει σε νέα επίπεδα για τον χαρακτηρισμό state of the art (SOTA), κατακτώντας την κορυφή του εξωτερικού πίνακα κατάταξης(ανοίγει σε νέο παράθυρο). Περιλαμβάνοντας ερωτήσεις σε τρία επίπεδα δυσκολίας, η επιτυχής ολοκλήρωση αυτών των εργασιών απαιτεί ικανότητες όπως η συλλογιστική, η πολυτροπική ευχέρεια, η περιήγηση στο διαδίκτυο και η επάρκεια στη χρήση εργαλείων.

GAIA
Επίπεδο 1Επίπεδο 2Επίπεδο 3Μέσος όρος
Προηγούμενη κορυφαία τεχνολογία(ανοίγει σε νέο παράθυρο)67,9267,4442,3163,64
Έρευνα σε βάθος (pass@1)74,2969,0647,667,36
Έρευνα σε βάθος (cons@64)78,6673,2158,0372,57

Παραδείγματα εργασιών 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.

[ενέργεια αναζήτησης]

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.

[ενέργεια περιήγησης]

Reflecting on potential issues

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

[ενέργεια περιήγησης]

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.

[ενέργεια αναζήτησης]

Pinpointing key features

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

[ενέργεια περιήγησης]

Piecing together insights

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

[ενέργεια αναζήτησης]

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.

[ενέργεια αναζήτησης]

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.

[ενέργεια αναζήτησης]

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.

[ενέργεια περιήγησης]

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.

[ενέργεια περιήγησης]

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."

[ενέργεια περιήγησης]

Evaluating library sources

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

[ενέργεια περιήγησης]

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.

[ενέργεια περιήγησης]

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.

[ενέργεια περιήγησης]

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.

[ενέργεια περιήγησης]

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.

[ενέργεια αναζήτησης]

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.

[ενέργεια αναζήτησης]

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.

[ενέργεια αναζήτησης]

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.

[ενέργεια αναζήτησης]

Εργασίες επιπέδου ειδικού

Σε μια εσωτερική αξιολόγηση εργασιών σε επίπεδο ειδικών σε διάφορους τομείς, η αξιολόγηση από ειδικούς του τομέα για την έρευνα σε βάθος έκρινε ότι έχει αυτοματοποιήσει πολλές ώρες δύσκολης, μη αυτόματης διερεύνησης. 

Ποσοστό επιτυχίας έναντι μέγιστων κλήσεων εργαλείων
Ποσοστό επιτυχίαςΜέγιστος αριθμός κλήσεων εργαλείων
Όσο περισσότερο το μοντέλο περιηγείται και σκέφτεται τι περιηγείται, τόσο καλύτερα αποδίδει, γι' αυτό και είναι σημαντικό να του δίνεται χρόνος για να σκεφτεί.
Παραδείγματα εργασιών επιπέδου ειδικού
Εξοικονόμηση χρόνου στην εργασία: 4 ώρες

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.

Κατανοώ τα μοντέλα ρόφησης

Συγκεντρώνω πληροφορίες σχετικά με τη ρόφηση καθαρών και μικτών αερίων σε υαλώδη πολυμερή, εστιάζοντας στο μοντέλο ρόφησης διπλής κατάστασης και αντιμετωπίζοντας τις προκλήσεις στις προβλέψεις μοντελοποίησης.

[ενέργεια αναζήτησης]

Αξιολογώ την ανοιχτή πρόσβαση

Εντάξει, για να δω. Το αποτέλεσμα από το MDPI για τη ρόφηση μικτών αερίων σε υαλώδη πολυμερή έχει πιθανώς ανοικτή πρόσβαση.

[ενέργεια περιήγησης]

[ενέργεια περιήγησης]

Εξέταση τμημάτων
Συγκεντρώνω πληροφορίες από το Μοντέλο ρόφησης διπλής κατάστασης και την εκτεταμένη ανάλυσή του στο πλαίσιο της δημοσίευσης του MDPI.

[ενέργεια περιήγησης]

Αποσαφηνίζω τις κύριες ιδιότητες

Εξετάζω την εργαστηριακή αναφορά για να καταλάβω τη σταθερά του νόμου του Χένρι, τη σταθερά συγγένειας του Λάνγκμουιρ και τη σταθερά χωρητικότητας του Λάνγκμουιρ, που περιγράφουν τη ρόφηση αερίου.

[ενέργεια περιήγησης]

Συνδυάζω πληροφορίες

Διερευνώ την πιθανότητα ότι οι εξισώσεις «Εξίσωση (3)» και «Εξίσωση (4)» μπορεί να είναι εικόνες ή αναπαραστάσεις τύπων και σκέφτομαι να συμβουλευτώ το PDF ή να αναζητήσω προηγούμενες αναφορές για να τις κατανοήσω καλύτερα.

[ενέργεια περιήγησης]

Επιβεβαιώνω τη συνάφεια του τίτλου

Επιβεβαιώνω αν το έγγραφο από τους Freeman και Koros (1980) αντιστοιχεί συγκεκριμένα στην αναφορά «Model for sorption of mixed gases in glassy polymers» (Μοντέλο για τη ρόφηση μικτών αερίων σε υαλώδη πολυμερή) ελέγχοντας την περίληψη και τον τίτλο.

[ενέργεια αναζήτησης]

Εξετάζω τις συνδέσεις μεταξύ άρθρων

Παρατήρησα ότι το αποτέλεσμα από το «pmc.ncbi.nlm.nih.gov» είναι πιθανώς το ίδιο άρθρο του MDPI και αναρωτιέμαι αν παρουσιάζει το κείμενο ή μια πιο απλοποιημένη έκδοση.

[ενέργεια περιήγησης]

[ενέργεια περιήγησης]

[ενέργεια περιήγησης]

Συγκεντρώνω πληροφορίες

Συγκεντρώνω πληροφορίες για τη ρόφηση καθαρών και μικτών αερίων σε υαλώδη πολυμερή. Αυτό είναι ένα κρίσιμο βήμα για την κατανόηση της συμπεριφοράς του υλικού σε διαφορετικά περιβάλλοντα αερίων.

[ενέργεια αναζήτησης]

Σύγκριση ρόφησης αερίου

Παρατήρησα ότι η παρουσία διοξειδίου του άνθρακα σε ένα μίγμα επηρεάζει τη ρόφηση μεθανίου στο πολυμερές, μειώνοντας τη ρόφηση μεθανίου σε σχέση με την περίπτωση καθαρού αερίου.

[ενέργεια περιήγησης]

Συνδέω έννοιες

Σκέφτομαι πώς ο όρος «εκτεταμένη εξίσωση διπλής κατάστασης για τα μίγματα» μπορεί να σχετίζεται με τις εξισώσεις υπεραγώγιμων καλωδίων διπλής κατάστασης. Φαίνονται να υπάρχουν δυνατότητες για σύνδεση των εννοιών μεταξύ αυτών των τομέων.

[ενέργεια αναζήτησης]

Ζητώ έλεγχο των λεπτομερειών

Σημειώνω το αίτημα για ανασκόπηση του άρθρου «Theories of Sorption and Transport in Polymer Membranes» (Θεωρίες ρόφησης και μεταφοράς σε πολυμερικές μεμβράνες).

[ενέργεια περιήγησης]

Ελέγχω τον σύνδεσμο PDF

Έχω περιέργεια για το Αποτέλεσμα [2] και εξερευνώ το απόσπασμα, το οποίο περιλαμβάνει την επέκταση ενός μοντέλου ρόφησης διπλής κατάστασης σε ένα δυαδικό μίγμα και την έκφραση της συγκέντρωσης του Α σε όρους μερικών πιέσεων και σταθερών.

[ενέργεια αναζήτησης]

Πρόβλεψη συμπεριφοράς ρόφησης

Το μοντέλο διπλής λειτουργίας προβλέπει ότι η προσθήκη ενός δεύτερου αερίου μειώνει τη ρόφηση σε σταθερή μερική πίεση, σε αντίθεση με τα σενάρια καθαρού αερίου.

[ενέργεια περιήγησης]

Βρίσκω ένα PDF

Μαζεύω πληροφορίες για ένα PDF από το nature.com, ίσως ένα παλιότερο άρθρο του Yampol'ski, αλλά σκέφτομαι εναλλακτικές πηγές όπως το αποθετήριο του Πανεπιστημίου του Τέξας στο Όστιν για ένα απόσπασμα κειμένου.

[ενέργεια περιήγησης]

Αξιολογώ τις επιλογές αποθετηρίου

Ανακάλυψα ότι το αποτέλεσμα του αποθετηρίου UT μπορεί να μην εμφανίζεται σωστά. Η αναζήτηση μέσα σε αυτό είναι αβέβαιη. Εναλλακτικά, το αποτέλεσμα [3] περιέχει ένα απόσπασμα που περιγράφει το μοντέλο ρόφησης μίγματος διπλής κατάστασης, εξηγώντας τις ανταγωνιστικές επιδράσεις και την καταλληλότητά του στη μοντελοποίηση πειραματικών δεδομένων.

[ενέργεια αναζήτησης]

Βελτιώνω την εστίαση

Προσαρμόζω την προσέγγισή μου για να διασφαλίσω ότι η αναζήτηση στοχεύει στο σωστό θεματικό πλαίσιο.

[ενέργεια αναζήτησης]

Κατανοώ τα μοντέλα ρόφησης

Αναλύω το μοντέλο ρόφησης διπλής λειτουργίας για τα καθαρά αέρια: τη διάλυση κατά Χένρι και την πλήρωση μικροκενών κατά Λάνγκμουιρ. Για τα μικτά αέρια, δίνεται έμφαση στην ανταγωνιστική ρόφηση και στις μη ιδανικές συμπεριφορές.

[ενέργεια αναζήτησης]

Εξερευνώ το hero.epa.gov

Σκέφτομαι την πιθανή περίληψη ή περιεχόμενο του hero.epa.gov

[ενέργεια περιήγησης]

Τελειοποιώ το μοντέλο

Συγκεντρώνω πληροφορίες σχετικά με τη ρόφηση καθαρών και μικτών αερίων, εξετάζοντας παράγοντες όπως ο ανταγωνισμός, η πλαστικοποίηση και η σταθερότητα των παραμέτρων. Ενσωματώνω τα δεδομένα μικτών αερίων για μεγαλύτερη ακρίβεια στις προβλέψεις.

[ενέργεια περιήγησης]

Αντιμετωπίζω τις προκλήσεις του μοντέλου ρόφησης διπλής κατάστασης

Προβλέψεις επιπτώσεων σύζευξης παραμέτρων και μη μοναδικότητας. Η απουσία αλλαγών στην κατάσταση του πολυμερούς μπορεί να οδηγήσει σε παραλείψεις.

[ενέργεια περιήγησης]

Ποσοτικοποιώ την απόκλιση

Ποσοτικοποιώ τη μη ιδανική διαλυτότητα CO2-CH4 σε 6Fda-MPDA, εμφανίζοντας τις επιδράσεις των μικτών αερίων στη διαλυτότητα. Η ανταγωνιστική ρόφηση δεν είναι ο μόνος λόγος που μειώνεται η εκλεκτικότητα της διαπερατότητας.

[ενέργεια περιήγησης]

Ενσωματώνω αναφορές

Συλλέγω παραπομπές, εστιάζοντας σε υλικά ανοιχτού κώδικα όπως το MDPI 2019 και το Vopicka 2014, για να υποστηρίξω τη συζήτηση σχετικά με τις διαφορές και τις προκλήσεις στο μοντέλο διπλής κατάστασης για τη ρόφηση αερίων σε πολυμερικές μεμβράνες.

[ενέργεια περιήγησης]

Προτείνω ενότητες

Οργανώνω ενότητες σχετικά με τη ρόφηση καθαρών έναντι μικτών αερίων, εξερευνώ το μοντέλο ρόφησης διπλής κατάστασης και περιγράφω λεπτομερώς προκλήσεις, όπως η αβεβαιότητα παραμέτρων και η πρόβλεψη μικτών αερίων.

Οργανώνω το περιεχόμενο

Εστιάζω στο μοντέλο ρόφησης διπλής κατάστασης, περιγράφοντας λεπτομερώς τις συμπεριφορές ρόφησης καθαρών και μικτών αερίων και τονίζοντας τις βασικές διαφορές και προκλήσεις σε λίστα με κουκκίδες και δομημένες ενότητες για σαφήνεια.

[ενέργεια αναζήτησης]

Επιλέγω τις παραπομπές

Εντάξει, για να δω. Βασίζομαι στους [3], [20], [22] και [21] για τις σαφείς γνώσεις τους σχετικά με την διπλή ρόφηση και τα μίγματα αερίων.

Χαρτογραφώ τις παραμέτρους

Συνδυάζω ονόματα παραμέτρων για να αποφύγω τυχόν σύγχυση. Διατηρώ τα (k), (C_H') και (b) για λόγους σαφήνειας. Οι εξισώσεις για τα καθαρά αέρια και για τα μίγματα είναι λεπτομερείς και σαφώς διατυπωμένες.

Αντιμετωπίζω τις τυχόν προκλήσεις

Ασχολούμαι με προσαρμογές παραμέτρων με πολλαπλές λύσεις, την πλαστικοποίηση πολυμερών και τις χρονικές επιδράσεις. Αυτές οι λεπτομέρειες καθιστούν δύσκολη την πρόβλεψη της ρόφησης καθαρών και μικτών αερίων.

Συνδυάζω πληροφορίες

Σχεδιάζω τη δομή ενοτήτων για τις διαφορές της ρόφησης, το μοντέλο διπλής λειτουργίας για τα καθαρά αέρια, την επέκτασή του στα μικτά αέρια και τις σχετικές προκλήσεις. Αυτή η εξέλιξη φαίνεται λογική και αποτελεσματική.

Ποσοστό επιτυχίας σε εργασίες επιπέδου ειδικού βάσει εκτιμώμενης οικονομικής αξίας
Ποσοστό επιτυχίαςΕκτιμώμενη οικονομική αξία
Ποσοστό επιτυχίας σε εργασίες επιπέδου ειδικού ανά εκτιμώμενες ώρες
Ποσοστό επιτυχίαςΕκτιμώμενες ώρες
Η εκτιμώμενη οικονομική αξία μιας εργασίας συσχετίζεται περισσότερο με το ποσοστό επιτυχίας παρά με τον αριθμό των ωρών που θα χρειαζόταν ένας άνθρωπος – τα πράγματα που δυσκολεύουν τα μοντέλα διαφέρουν από αυτά που οι άνθρωποι θεωρούν χρονοβόρα.

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.

Τι ακολουθεί

Η έρευνα σε βάθος είναι διαθέσιμη σήμερα στο ChatGPT στο web και θα κυκλοφορήσει σε εφαρμογές για κινητές συσκευές και υπολογιστές εντός του μήνα. Προς το παρόν, η έρευνα σε βάθος μπορεί να έχει πρόσβαση στο ανοιχτό web και σε οποιαδήποτε αρχεία έχετε ανεβάσει. Στο μέλλον, θα μπορείτε να συνδεθείτε με πιο εξειδικευμένες πηγές δεδομένων, επεκτείνοντας την πρόσβασή τους σε πόρους που βασίζονται σε συνδρομές ή σε εσωτερικούς πόρους, ώστε να γίνεται το αποτέλεσμα ακόμη πιο ισχυρό και εξατομικευμένο.

Κοιτάζοντας πιο μπροστά, οραματιζόμαστε εμπειρίες όπου το ChatGPT θα λειτουργεί αυτόνομα, πραγματοποιώντας ασύγχρονη έρευνα και εκτέλεση στον πραγματικό κόσμο. Ο συνδυασμός της έρευνας σε βάθος, που μπορεί να εκτελεί ασύγχρονη διαδικτυακή συλλογή στοιχείων, και του Operator, που μπορεί να ενεργεί στον πραγματικό κόσμο, θα επιτρέψει στο ChatGPT να εκτελεί όλο και πιο εξελιγμένες εργασίες για λογαριασμό σας.


Παράρτημα 3 Φεβρουαρίου 2025: Πραγματοποιήσαμε αυστηρούς ελέγχους ασφάλειας, αξιολογήσεις ετοιμότητας και αναθεωρήσεις διακυβέρνησης στην πρώιμη έκδοση του o3 που τροφοδοτεί την έρευνα σε βάθος, προσδιορίζοντάς την ως Μεσαίου(ανοίγει σε νέο παράθυρο) κινδύνου. Πραγματοποιήσαμε επίσης πρόσθετες δοκιμές ασφάλειας για την καλύτερη κατανόηση των επιπρόσθετων κινδύνων που σχετίζονται με την ικανότητα της έρευνας σε βάθος να περιηγείται στο Web, και προσθέσαμε νέες μεθόδους μετριασμού. Θα συνεχίσουμε να δοκιμάζουμε διεξοδικά και να παρακολουθούμε στενά την τρέχουσα περιορισμένη έκδοση. Θα μοιραστούμε τις πληροφορίες ασφαλείας και τα μέτρα ασφαλείας μας για την έρευνα σε βάθος σε μια κάρτα συστήματος όταν διευρύνουμε την πρόσβαση στους χρήστες 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, Zhiqing Sun

Foundational Contributors

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