Our data Browse feeds Sign in Create account
           1. Releasebot
           2. |
           3. All Release Notes

          OpenAI Release Notes

          Follow

      Last updated: Dec 12, 2025

        RSS Email API Slack n8n Zapier

    OpenAI Products

          * ChatGPT
            98 releases
          * ChatGPT Atlas
            20 releases
          * ChatGPT Business
            34 releases
          * ChatGPT Enterprise/EDU
            51 releases
          * Codex
            55 releases
          * OpenAI Models
            33 releases

    All OpenAI Release Notes

        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              ChatGPT by OpenAI

                December 11, 2025

              GPT-5.2 rolls out across Instant, Thinking, and Pro, boosting accuracy, usefulness, and structured reasoning for work, learning, and complex tasks. It adds Aug 2025 knowledge and new default: free users get Instant by default with optional Thinking reasoning.

                  GPT-5.2 Release Notes

                  Today, we’re releasing GPT-5.2, the next upgrade to the GPT-5 series. GPT-5.2 is smarter and more useful for both work and learning—while remaining just as enjoyable to talk to. As with GPT-5.1, we’re continuing to improve our main models for everyone on a regular basis to make them more useful and enjoyable to use.

                  GPT-5.2 Instant

                  GPT-5.2 Instant is a fast yet powerful workhorse for everyday work and learning, with clear improvements in info-seeking questions, how-tos and walk-throughs, technical writing, and translation, all while retaining the warmer, more conversational tone introduced in GPT-5.1 Instant. Early testers noted its more clearly structured explanations where important info is highlighted upfront. It’s also more effective at supporting studying and skill-building, as well as offering clearer job and career guidance.

                  GPT-5.2 Thinking

                  GPT-5.2 Thinking solves harder work tasks more effectively and with more polish—particularly in spreadsheet formatting and financial modeling, alongside improvements in slideshow creation. Early testing showed gains in coding, summarizing long documents, answering questions about uploaded files, walking through complex math and logic step by step, and helping with planning and decision-making with clearer structure and thoughtful detail.

                  GPT-5.2 Pro

                  GPT-5.2 Pro is our smartest and most trustworthy model yet for difficult questions where a higher-quality answer is worth the wait. In early testing, it shows fewer major errors and stronger performance across complex domains like programming.

                  All three models (Instant, Thinking, and Pro) have a new knowledge cutoff of August 2025. For users, this means GPT-5.2 starts with a more current understanding of the world, so answers are more accurate and useful, with more relevant examples and context, even before turning to web search.

                  Read our blog for more details on examples and evals.

                  Update for free and Go users: We’re removing automatic model switching for reasoning in ChatGPT. Previously, some questions were automatically routed to the Thinking model when ChatGPT determined it might help. To maximize choice, free users will now use GPT-5.2 Instant by default, and can still choose to use reasoning anytime by selecting Thinking from the tools menu in the message composer.

                  Original source Report a problem
                  Show more
        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              OpenAI

                Introducing GPT-5.2

              GPT‑5.2 marks a major leap for professional knowledge work, delivering faster, cheaper, and more capable AI across spreadsheets, code, long-context analysis, and multi‑step workflows. With new safety, tooling, and enterprise rollout, it’s now available to paid plans today.

                  GPT‑5.2 release notes

                  We are introducing GPT‑5.2, the most capable model series yet for professional knowledge work.
                  Already, the average ChatGPT Enterprise user says⁠ AI saves them 40–60 minutes a day, and heavy users say it saves them more than 10 hours a week. We designed GPT‑5.2 to unlock even more economic value for people; it’s better at creating spreadsheets, building presentations, writing code, perceiving images, understanding long contexts, using tools, and handling complex, multi-step projects.
                  GPT‑5.2 sets a new state of the art across many benchmarks, including GDPval, where it outperforms industry professionals at well-specified knowledge work tasks spanning 44 occupations.

                  GPT‑5.2 Thinking is the best model yet for real-world, professional use. On GDPval, an eval measuring well-specified knowledge work tasks across 44 occupations, GPT‑5.2 Thinking sets a new state-of-the-art score, and is our first model that performs at or above a human expert level. Specifically, GPT‑5.2 Thinking beats or ties top industry professionals on 70.9% of comparisons on GDPval knowledge work tasks, according to expert human judges. These tasks include making presentations, spreadsheets, and other artifacts. GPT‑5.2 Thinking produced outputs for GDPval tasks at >11x the speed and <1% the cost of expert professionals, suggesting that when paired with human oversight, GPT‑5.2 can help with professional work. Speed and cost estimates are based on historical metrics; speed in ChatGPT may vary.

                  When reviewing one especially good output, one GDPval judge commented, "It is an exciting and noticeable leap in output quality... [it] appears to have been done by a professional company with staff, and has a surprisingly well designed layout and advice for both deliverables, though with one we still have some minor errors to correct."

                  Additionally, on our internal benchmark of junior investment banking analyst spreadsheet modeling tasks—such as putting together a three-statement model for a Fortune 500 company with proper formatting and citations, or building a leveraged buyout model for a take-private—GPT 5.2 Thinking's average score per task is 9.3% higher than GPT‑5.1’s, rising from 59.1% to 68.4%.

                  Side-by-side comparisons show improved sophistication and formatting in spreadsheets and slides generated by GPT‑5.2 Thinking.

                  To use the new spreadsheet and presentation capabilities in ChatGPT, you must be on a Plus, Pro, Business, or Enterprise plan and select either GPT‑5.2 Thinking or Pro. Complex generations can take many minutes to produce.

                  GPT‑5.2 Thinking sets a new state of the art of 55.6% on SWE-Bench Pro, a rigorous evaluation of real-world software engineering. Unlike SWE-bench Verified, which only tests Python, SWE-Bench Pro tests four languages and aims to be more contamination-resistant, challenging, diverse, and industrially relevant.

                  On SWE-bench Verified (not plotted), GPT‑5.2 Thinking scores our new high of 80%.

                  For everyday professional use, this translates into a model that can more reliably debug production code, implement feature requests, refactor large codebases, and ship fixes end-to-end with less manual intervention.

                  GPT‑5.2 Thinking is also better at front-end software engineering than GPT‑5.1 Thinking. Early testers found it significantly stronger at front-end development and complex or unconventional UI work—especially involving 3D elements—making it a powerful daily partner for engineers across the stack.

                  Early testers shared their feedback on GPT‑5.2’s coding capabilities, including a quote from Jeff Wang, CEO of Windsurf, praising it as the biggest leap for GPT models in agentic coding since GPT-5 and a state-of-the-art coding model in its price range.

                  GPT‑5.2 Thinking hallucinates less than GPT‑5.1 Thinking. On a set of de-identified queries from ChatGPT, responses with errors were 30% less common. For professionals, this means fewer mistakes when using the model for research, writing, analysis, and decision support—making the model more dependable for everyday knowledge work.

                  GPT‑5.2 Thinking sets a new state of the art in long-context reasoning, achieving leading performance on OpenAI MRCRv2—an evaluation that tests a model’s ability to integrate information spread across long documents. On real-world tasks like deep document analysis, which require related information across hundreds of thousands of tokens, GPT‑5.2 Thinking is substantially more accurate than GPT‑5.1 Thinking. In particular, it’s the first model we’ve seen that achieves near 100% accuracy on the 4-needle MRCR variant (out to 256k tokens).

                  This enables professionals to use GPT‑5.2 to work with long documents—such as reports, contracts, research papers, transcripts, and multi-file projects—while maintaining coherence and accuracy across hundreds of thousands of tokens. This makes GPT‑5.2 especially well suited for deep analysis, synthesis, and complex multi-source workflows.

                  GPT‑5.2 Thinking is our strongest vision model yet, cutting error rates roughly in half on chart reasoning and software interface understanding.

                  For everyday professional use, this means the model can more accurately interpret dashboards, product screenshots, technical diagrams, and visual reports—supporting workflows in finance, operations, engineering, design, and customer support where visual information is central.

                  Compared to previous models, GPT‑5.2 Thinking has a stronger grasp of how elements are positioned within an image, which helps on tasks where relative layout plays a key role in solving the problem. Even on a low-quality image, GPT‑5.2 identifies the main regions and places boxes that sometimes match the true locations of each component, while GPT‑5.1 only labels a few parts and shows a much weaker understanding of their spatial arrangement.

                  GPT‑5.2 Thinking achieves a new state of the art of 98.7% on Tau2-bench Telecom, demonstrating its ability to reliably use tools across long, multi-turn tasks.

                  For latency-sensitive use cases, GPT‑5.2 Thinking also performs much better at reasoning.effort='none', substantially outperforming GPT‑5.1 and GPT‑4.1.

                  For professionals, this translates into stronger end-to-end workflows—such as resolving customer support cases, pulling data from multiple systems, running analyses, and generating final outputs with fewer breakdowns between steps.

                  For example, when asking a complex customer service question that requires multi-step resolution, the model can more effectively coordinate a full workflow across multiple agents. In the case below, a traveler reports a delayed flight, a missed connection, an overnight stay in New York, and a medical seating requirement. GPT‑5.2 manages the entire chain of tasks—rebooking, special-assistance seating, and compensation—delivering a more complete outcome than GPT‑5.1.

                  One of our hopes for AI is that it will accelerate scientific research for the benefit of everyone. Toward this, we’ve been working with and listening to scientists to see how AI can speed up their work, and last month we shared some early collaborative experiments here.

                  We believe GPT‑5.2 Pro and GPT‑5.2 Thinking are the world’s best models for assisting and accelerating scientists. On GPQA Diamond, a graduate-level Google-proof Q&A benchmark, GPT‑5.2 Pro achieves 93.2%, followed closely by GPT‑5.2 Thinking at 92.4%.

                  On FrontierMath (Tier 1–3), an evaluation of expert-level mathematics, GPT‑5.2 Thinking set a new state of the art, solving 40.3% of problems.

                  We're beginning to see AI models meaningfully accelerate progress in math and science in tangible ways. For example, in recent work with GPT‑5.2 Pro, researchers explored an open question in statistical learning theory. In a narrow, well-specified setting, the model proposed a proof that was subsequently verified by the authors and reviewed with external experts, illustrating how frontier models can assist mathematical research under close human oversight.

                  On ARC-AGI-1 (Verified), a benchmark designed to measure general reasoning ability, GPT‑5.2 Pro is the first model to cross the 90% threshold, improving from 87% by o3‑preview last year while reducing the cost of achieving that performance by roughly 390×.

                  On ARC-AGI-2 (Verified), which raises the difficulty and better isolates fluid reasoning, GPT‑5.2 Thinking achieves a new state of the art for chain-of-thought models, scoring 52.9%. GPT‑5.2 Pro performs even higher, reaching 54.2%, further extending the model’s ability to reason through novel, abstract problems.

                  Improvements across these evaluations reflect GPT‑5.2’s stronger multi-step reasoning, greater quantitative accuracy, and more reliable problem solving on complex technical tasks.

                  Here’s what our early testers say about GPT‑5.2:
                  "GPT-5.2 unlocked a complete architecture shift for us. We collapsed a fragile, multi-agent system into a single mega-agent with 20+ tools. The best part is, it just works. The mega-agent is faster, smarter, and 100x easier to maintain. We’re seeing dramatically lower latency, much stronger tool calling, and we no longer need sprawling system prompts because 5.2 will execute cleanly off a simple, one-line prompt. It feels like pure magic."
                  AJ Orbach, CEO, Triple Whale

                  In ChatGPT, users should notice GPT‑5.2 feels better to use day to day—more structured, more reliable, and still enjoyable to talk to.

                  GPT‑5.2 Instant is a fast, capable workhorse for everyday work and learning, with clear improvements in info-seeking questions, how-tos and walk-throughs, technical writing, and translation, building on the warmer conversational tone introduced in GPT‑5.1 Instant. Early testers particularly noted clearer explanations that surface key information upfront.

                  GPT‑5.2 Thinking is designed for deeper work, helping users tackle more complex tasks with greater polish—especially for coding, summarizing long documents, answering questions about uploaded files, working through math and logic step by step, and supporting planning and decisions with clearer structure and more useful detail.

                  GPT‑5.2 Pro is our smartest and most trustworthy option for difficult questions where a higher-quality answer is worth the wait, with early testing showing fewer major errors and stronger performance in complex domains like programming.

                  GPT‑5.2 builds on the safe completion research we introduced with GPT‑5, which teaches the model to give the most helpful answer while still staying within safety boundaries.

                  With this release, we continued our work to strengthen our models’ responses in sensitive conversations, with meaningful improvements in how they respond to prompts indicating signs of suicide or self harm, mental health distress, or emotional reliance on the model. These targeted interventions have resulted in fewer undesirable responses in both GPT‑5.2 Instant and GPT‑5.2 Thinking as compared to GPT‑5.1 and GPT‑5 Instant and Thinking models. Further details can be found in the system card.

                  We’re in the early stages of rolling out our age prediction model so that we can automatically apply content protections for users who are under 18, in order to limit access to sensitive content. This builds on our existing approach to users we know are under 18 and our parental controls.

                  GPT‑5.2 is one step in an ongoing series of improvements, and we’re far from done. While this release delivers meaningful gains in intelligence and productivity, we know there are areas where people want more. In ChatGPT, we’re working on known issues like over-refusals, while continuing to raise the bar on safety and reliability overall. These changes are complex, and we’re focused on getting them right.

                  In ChatGPT, we’ll begin rolling out GPT‑5.2 (Instant, Thinking, and Pro) today, starting with paid plans (Plus, Pro, Go, Business, Enterprise). We deploy GPT‑5.2 gradually to keep ChatGPT as smooth and reliable as we can; if you don’t see it at first, please try again later. In ChatGPT, GPT‑5.1 will still be available to paid users for three months under legacy models, after which we will sunset GPT‑5.1.

                  In our API Platform, GPT‑5.2 Thinking is available today in the Responses API and Chat Completions API as gpt-5.2, and GPT‑5.2 Instant as gpt-5.2-chat-latest. GPT‑5.2 Pro is available in the Responses API as gpt-5.2-pro. Developers can now set the reasoning parameter in GPT‑5.2 Pro, and both GPT‑5.2 Pro and GPT‑5.2 Thinking now support the new fifth reasoning effort of xhigh, for tasks where quality is most important.

                  GPT‑5.2 is priced at $1.75/1M input tokens and $14/1M output tokens, with a 90% discount on cached inputs. On multiple agentic evals, we found that despite GPT‑5.2’s greater cost per token, the cost of attaining a given level of quality ended up less expensive due to GPT‑5.2’s greater token efficiency.

                  While ChatGPT subscription pricing remains the same, in the API GPT‑5.2 is priced higher per token than GPT‑5.1 because it is a more capable model. It’s still priced below other frontier models, so people can continue to use it deeply in their daily work and core applications.

                  GPT‑5.2 was built in collaboration with our long-standing partners NVIDIA and Microsoft. Azure data centers and NVIDIA GPUs, including H100, H200, and GB200-NVL72, underpin OpenAI’s at-scale training infrastructure, driving significant gains in model intelligence. Together, this collaboration allows us to scale compute with confidence and bring new models to market more quickly.

                  Original source Report a problem
                  Show more
        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              OpenAI

                The Walt Disney Company and OpenAI reach landmark agreement to bring beloved characters from across Disney’s brands to Sora

              Disney and OpenAI announce a three year licensing deal to power Sora and ChatGPT Images with Disney IP. Fans will create and stream short videos on Disney+ starting early 2026, with OpenAI APIs enabling new experiences. The pact stresses responsible AI and creator rights.

                  Agreement overview

                    + Agreement marks a significant step in setting meaningful standards for responsible AI in entertainment.
                    + As part of this three-year licensing agreement, Sora will be able to generate short, user-prompted social videos that can be viewed and shared by fans, drawing on more than 200 Disney, Marvel, Pixar and Star Wars characters.
                    + Agreement will make a selection of these fan-inspired Sora short form videos available to stream on Disney+.
                    + Disney and OpenAI affirm a shared commitment to responsible use of AI that protects the safety of users and the rights of creators.
                    + Alongside the licensing agreement, Disney will become a major customer of OpenAI, using its APIs to build new products, tools, and experiences, including for Disney+, and deploying ChatGPT for its employees.
                    + As part of the agreement, Disney will make a $1 billion equity investment in OpenAI, and receive warrants to purchase additional equity.

                  The Walt Disney Company and OpenAI have reached an agreement for Disney to become the first major content licensing partner on Sora, OpenAI’s short-form generative AI video platform, bringing these leaders in creativity and innovation together to unlock new possibilities in imaginative storytelling.

                  As part of this new, three-year licensing agreement, Sora will be able to generate short, user-prompted social videos that can be viewed and shared by fans, drawing from a set of more than 200 animated, masked and creature characters from Disney, Marvel, Pixar and Star Wars, including costumes, props, vehicles, and iconic environments. In addition, ChatGPT Images will be able to turn a few words by the user into fully generated images in seconds, drawing from the same intellectual property. The agreement does not include any talent likenesses or voices.

                  Alongside the licensing agreement, Disney will become a major customer of OpenAI, using its APIs to build new products, tools, and experiences, including for Disney+, and deploying ChatGPT for its employees.

                  As part of the agreement, Disney will make a $1 billion equity investment in OpenAI, and receive warrants to purchase additional equity.

                  Under the agreement, Disney and OpenAI are affirming a shared commitment to the responsible use of AI that protects user safety and the rights of creators. Together, the companies will advance human-centered AI that respects the creative industries and expands what is possible for storytelling.

                  The transaction is subject to the negotiation of definitive agreements, required corporate and board approvals, and customary closing conditions.

                  “Technological innovation has continually shaped the evolution of entertainment, bringing with it new ways to create and share great stories with the world,” said Robert A. Iger, CEO, The Walt Disney Company. “The rapid advancement of artificial intelligence marks an important moment for our industry, and through this collaboration with OpenAI we will thoughtfully and responsibly extend the reach of our storytelling through generative AI, while respecting and protecting creators and their works. Bringing together Disney’s iconic stories and characters with OpenAI’s groundbreaking technology puts imagination and creativity directly into the hands of Disney fans in ways we’ve never seen before, giving them richer and more personal ways to connect with the Disney characters and stories they love.”

                  “Disney is the global gold standard for storytelling, and we’re excited to partner to allow Sora and ChatGPT Images to expand the way people create and experience great content,” said Sam Altman, co-founder and CEO of OpenAI. “This agreement shows how AI companies and creative leaders can work together responsibly to promote innovation that benefits society, respect the importance of creativity, and help works reach vast new audiences.”

                  Under the license, fans will be able to watch curated selections of Sora-generated videos on Disney+, and OpenAI and Disney will collaborate to utilize OpenAI’s models to power new experiences for Disney + subscribers, furthering innovative and creative ways to connect with Disney’s stories and characters.

                  Sora and ChatGPT Images are expected to start generating fan-inspired videos with Disney’s multi-brand licensed characters in early 2026.

                  Among the characters fans will be able to use in their creations are Mickey Mouse, Minnie Mouse, Lilo, Stitch, Ariel, Belle, Beast, Cinderella, Baymax, Simba, Mufasa, as well as characters from the worlds of Encanto, Frozen, Inside Out, Moana, Monsters Inc., Toy Story, Up, Zootopia, and many more; plus iconic animated or illustrated versions of Marvel and Lucasfilm characters like Black Panther, Captain America, Deadpool, Groot, Iron Man, Loki, Thor, Thanos, Darth Vader, Han Solo, Luke Skywalker, Leia, the Mandalorian, Stormtroopers, Yoda and more.

                  As part of the agreement, OpenAI has committed to continuing its industry leadership in implementing responsible measures to further address trust and safety, including age-appropriate policies and other reasonable controls across the service. In addition, OpenAI and Disney have affirmed a shared commitment to maintaining robust controls to prevent the generation of illegal or harmful content, to respect the rights of content owners in relation to the outputs of models, and to respect the rights of individuals to appropriately control the use of their voice and likeness.

                  Original source Report a problem
                  Show more
        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              Codex by OpenAI

                Codex CLI 0.71.0

                  $ npm install -g @openai/[email protected]
                  Original source Report a problem
        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              OpenAI

                Advancing science and math with GPT-5.2

              GPT‑5.2 Pro and Thinking push AI-driven science forward with stronger mathematical reasoning, new benchmarks, and real case studies showing AI helping solve open problems while emphasizing careful human verification.

                  GPT‑5.2 is our strongest model yet for math and science work.

                  One of our hopes for strong AI is that it will accelerate scientific research for the benefit of everyone, helping researchers explore more ideas, test them faster, and turn discoveries into impact.

                  Over the past year, we’ve been working closely with scientists across math, physics, biology, and computer science to understand where AI can help—and where it still falls short. Last month, we published a paper⁠ that compiles early case studies across math, physics, biology, computer science, astronomy, and materials science in which GPT‑5 helped researchers showing how GPT‑5 has already begun contributing to real scientific work. With GPT‑5.2, we’re starting to see those gains become more consistent and more reliable.

                  Stronger performance where precision matters

                  GPT‑5.2 Pro and GPT‑5.2 Thinking are our strongest models yet for scientific and mathematical work.

                  Strong mathematical reasoning is a foundation for reliability in scientific and technical work. It enables models to follow multi-step logic, keep quantities consistent, and avoid subtle errors that can compound in real analyses—from simulations and statistics to forecasting and modeling. Improvements on benchmarks like FrontierMath reflect not a narrow skill, but stronger general reasoning and abstraction, capabilities that carry directly into scientific workflows such as coding, data analysis, and experimental design.

                  These capabilities are also closely tied to progress toward general intelligence. A system that can reliably reason through abstraction, maintain consistency across long chains of thought, and generalize across domains is exhibiting traits that are foundational to AGI—not task-specific tricks, but broad, transferable reasoning skills that matter across science, engineering, and real-world decision-making.

                  We believe GPT‑5.2 Pro and GPT‑5.2 Thinking are the world’s best models for assisting and accelerating scientists. On GPQA Diamond, a graduate-level Google-proof Q&A benchmark, GPT‑5.2 Pro achieves 93.2%, followed closely by GPT‑5.2 Thinking at 92.4%.

                  In GPQA Diamond, models answer multiple choice questions about physics, chemistry, and biology. No tools were enabled and reasoning effort was set to maximum.

                  On FrontierMath (Tier 1–3), an evaluation of expert-level mathematics, GPT‑5.2 Thinking set a new state of the art, solving 40.3% of problems.

                  In FrontierMath, models solve expert-level mathematics problems. A Python tool was enabled and reasoning effort was set to maximum.

                  Case study

                  GPT‑5.2 is not only strong at graduate-level science problems. We now regularly see our frontier models contributing solutions to previously unsolved—and increasingly subtle—questions in mathematics and the sciences.

                  In this case study, we describe how GPT‑5.2 Pro helped resolve an open research problem in statistical learning theory, documented in a new paper, On Learning-Curve Monotonicity for Maximum Likelihood Estimators.

                  The question (“If you collect more data, do your results reliably get better?”) shows up any time you fit a model from data. You can draw a learning curve that tracks average error as you add more examples. In the best case, the curve is monotone. More data means less error, every step of the way. That is the behavior people hope for, and often assume.

                  But over the last few years, researchers have learned that this intuition can fail. A line of work kicked off by an open problem posed at the Conference on Learning Theory (COLT) in 2019 by Viering, Mey, and Loog showed that the answer is often no. Even very simple, well-behaved toy setups can have non-monotonic learning curves, where adding data increases expected error. That surprise triggered a wave of follow-up papers. They expanded the list of settings where these reversals happen and proposed increasingly elaborate methods designed to restore monotone behavior.

                  Still, one of the most basic cases remained unresolved. What happens in the cleanest textbook situation, where the statistical model is actually correct and the data follow the familiar bell curve pattern, with a known mean but unknown standard deviation? Researchers already knew that small changes to this setup could break monotonic behavior. But the answer remained unknown in this core case.

                  Our new paper demonstrates that in this clean setting, intuition prevails: learning is predictably improved by more data, rather than behaving in surprising or unstable ways. What makes this paper unusual is how the proof was obtained. The authors did not work out a strategy and then ask the model to fill in steps. They did not provide intermediate arguments or a proof outline. Instead, they asked GPT‑5.2 Pro to solve the open problem directly, and then carefully verified the proof, including review and validation by external subject-matter experts.

                  The authors then asked simple follow-up questions to see how far the idea could go. GPT‑5.2 Pro extended the result beyond the original problem to higher dimensional settings and other common statistical models. Throughout, the human role stayed focused on verification and clear writing, rather than supplying mathematical scaffolding.

                  Looking ahead

                  This result suggests a useful direction for how AI systems can support scientific research, particularly in domains with axiomatic theoretical foundations such as mathematics and theoretical computer science. In settings like these, frontier models can help explore proofs, test hypotheses, and identify connections that might otherwise take substantial human effort to uncover.

                  At the same time, these systems are not independent researchers. Expert judgment, verification, and domain understanding remain essential. Even highly capable models can make mistakes or rely on unstated assumptions. But they can also produce detailed, structured arguments that merit careful human study and refinement. Making reliable progress with AI therefore depends on workflows that keep validation, transparency, and collaboration firmly in the loop.

                  Viewed as a case study, this result illustrates an emerging mode of research practice. Models like GPT‑5.2 can serve as tools for supporting mathematical reasoning and accelerating early-stage exploration, while responsibility for correctness, interpretation, and context remains with human researchers. Used carefully, such systems may help streamline significant aspects of theoretical work without displacing the central role of human judgment in scientific inquiry.

                  Original source Report a problem
                  Show more
        * Dec 11, 2025
              + Parsed from source:
              Dec 11, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              ChatGPT Enterprise/EDU by OpenAI

                December 11, 2025

              GPT-5.2 arrives with stronger artifact creation and longer context for professional work. Enterprise and Edu Early Access with admin controls; custom GPTs migrate by Jan 12, 2026. Credits stay the same.

                  GPT-5.2 Release Notes

                  Overview

                  This week, we’re rolling out GPT-5.2, the most capable model series yet for professional knowledge work with improved work artifact creation like spreadsheets, tool use and longer context retrieval. As with GPT-5.1, we’re continuing to improve our main models for everyone on a regular basis to make them more useful and enjoyable to use.

                  Availability

                  We’re releasing GPT-5.2 to Enterprise and Edu workspaces in Early Access, meaning you can turn it on now for your workspace in admin settings, where you can also manage access to legacy models. We’ll be transitioning custom GPTs to GPT-5.2 on January 12, 2026, and we recommend GPT creators switch as early as possible.

                  Pricing

                  The credits for GPT-5.2 will remain the same as GPT-5. See the current ChatGPT rate card for pricing information.

                  Original source Report a problem
                  Show more
        * Dec 10, 2025
              + Parsed from source:
              Dec 10, 2025
              + Detected by Releasebot:
              Dec 4, 2025
              + Modified by Releasebot:
              Dec 13, 2025

              Codex by OpenAI

                Codex CLI 0.69.0

                  $ npm install -g @openai/[email protected]
                  Original source Report a problem
        * Dec 9, 2025
              + Parsed from source:
              Dec 9, 2025
              + Detected by Releasebot:
              Dec 10, 2025

              ChatGPT Atlas by OpenAI

                December 9th, 2025

              New onboarding flow for Ask ChatGPT sidebar and a bundle of fixes and UI tweaks. Highlights include memory from webpages, smoother full screen video animation, devtools paste fixes, vertical tabs improvements and a public LGPL bundle link.

                  Onboarding

                  First time onboarding flow for Ask ChatGPT sidebar

                  Bugs

                    + Bug fixes for occasional empty chat + search responses
                    + Bug fixes for 'all tabs are blank' issue
                    + Improved full screen video animation

                  Browser memories

                  Right click on text on a webpage and select "Ask ChatGPT to remember" to add text from webpages to your ChatGPT memory

                  Dev tools

                    + Copy and paste fix for devtools

                  Vertical tabs

                    + Hover to see tabs: Hover left side of screen to see tabs, when tabs are closed in vertical tabs setting
                    + Add tab close button when you're in vertical tabs 'mini' mode (very narrow width)
                    + Tab style: Ability to set vertical tabs from "Tab Style" menu in main tabs menu

                  Public link to LGPL bundle

                  https://persistent.oaistatic.com/atlas/public/lgpl/1.2025.337.4.tar.gz.

                  Original source Report a problem
                  Show more
        * Dec 4, 2025
              + Parsed from source:
              Dec 4, 2025
              + Detected by Releasebot:
              Dec 12, 2025

              Codex by OpenAI

                Introducing Codex for Linear

                  Assign or mention @Codex in an issue to kick-off a Codex cloud task. As Codex works, it posts updates back to Linear, providing a link to the completed task so you can review, open a PR, or keep working.

                  To learn more about how to connect Codex to Linear both locally through MCP and through the new integration, check out the Codex for Linear documentation.

                  Original source Report a problem
        * Dec 4, 2025
              + Parsed from source:
              Dec 4, 2025
              + Detected by Releasebot:
              Nov 25, 2025
              + Modified by Releasebot:
              Dec 9, 2025

              Codex by OpenAI

                Codex CLI 0.65.0

                  Command

                  $ npm install -g @openai/[email protected]

                  View details

                  Original source Report a problem
      Load more updates

    Related vendors

        * Anthropic
        * Google
        * Perplexity
        * Apple
        * Cursor
        * xAI
  Index About Contact Terms Privacy © 2025 Releasebot