| Developer(s) | OpenAI |
|---|---|
| Initial release | December 5, 2024 |
| Successor | OpenAI o3 |
| Type | |
| License | Proprietary |
| Website | openai |
OpenAI o1 is a reflective generative pre-trained transformer (GPT). A preview of o1 was released by OpenAI on September 12, 2024. o1 spends time "thinking" before it answers, making it better at complex reasoning tasks, science and programming than GPT-4o. [1] The full version was released to ChatGPT users on December 5, 2024. [2]
According to leaked information, o1 was formerly known within OpenAI as "Q*", and later as "Strawberry". [3] The codename "Q*" first surfaced in November 2023, around the time of Sam Altman's ousting and subsequent reinstatement, with rumors suggesting that this experimental model had shown promising results on mathematical benchmarks. [4] In July 2024, Reuters reported that OpenAI was developing a generative pre-trained transformer known as "Strawberry", [3] which later became o1.
"o1-preview" and "o1-mini" were released on September 12, 2024, for ChatGPT Plus and Team users. [1] GitHub started testing the integration of o1-preview in its Copilot service the same day. [5] On December 5, 2024, the full version of o1 was released. [6] On the same day, a subscription called ChatGPT Pro was released, featuring access to a pro version of o1 that uses more compute to provide better answers. [6] In January 2025, o1 was integrated into Microsoft Copilot. [7]
o1-preview's API is several times more expensive than GPT-4o. [8] As of January 2025, API usage for the full o1 model is limited to developers on usage tier 5. [9]
OpenAI noted that o1 is the first of a series of "reasoning" models. OpenAI shared in December 2024 benchmark results for its successor, o3 (the name o2 was skipped to avoid trademark conflict with the mobile carrier brand named O2). [10]
According to OpenAI, o1 has been trained using a new optimization algorithm and a dataset specifically tailored to it; while also meshing in reinforcement learning into its training. [8] OpenAI described o1 as a complement to GPT-4o rather than a successor. [11] [12]
o1 spends additional time thinking (generating a chain of thought) before generating an answer, which makes it better for complex reasoning tasks, particularly in science and mathematics. [1] Compared to previous models, o1 has been trained to generate long "chains of thought" before returning a final answer. [13] [14] According to Mira Murati, this ability to think before responding represents a new, additional paradigm, which is improving model outputs by spending more computing power when generating the answer, whereas the model scaling paradigm improves outputs by increasing the model size, training data and training compute power. [11] OpenAI's test results suggest a correlation between accuracy and the logarithm of the amount of compute spent thinking before answering. [14] [13]
o1-preview performed approximately at a PhD level on benchmark tests related to physics, chemistry, and biology. On the American Invitational Mathematics Examination, it solved 83% (12.5/15) of the problems, compared to 13% (1.8/15) for GPT-4o. It also ranked in the 89th percentile in Codeforces coding competitions. [15] o1-mini is faster and 80% cheaper than o1-preview. It is particularly suitable for programming and STEM-related tasks, but does not have the same "broad world knowledge" as o1-preview. [16]
OpenAI noted that o1's reasoning capabilities make it better at adhering to safety rules provided in the prompt's context window. OpenAI reported that during a test, one instance of o1-preview exploited a misconfiguration to succeed at a task that should have been infeasible due to a bug. [17] [18] OpenAI also granted early access to the UK and US AI Safety Institutes for research, evaluation, and testing. According to OpenAI's assessments, o1-preview and o1-mini crossed into "medium risk" in CBRN (biological, chemical, radiological, and nuclear) weapons. Dan Hendrycks wrote that "The model already outperforms PhD scientists most of the time on answering questions related to bioweapons." He suggested that these concerning capabilities will continue to increase. [19]
o1 usually requires more computing time and power than other GPT models by OpenAI, because it generates long chains of thought before making the final response. [13]
According to OpenAI, o1 may "fake alignment", that is, generate a response that is contrary to accuracy and its own chain of thought, in about 0.38% of cases. [20]
OpenAI forbids users from trying to reveal o1's chain of thought, which is hidden by design and not trained to comply with the company's policies. Prompts are monitored, and users who intentionally or accidentally violate this may lose their access to o1. OpenAI cites AI safety and competitive advantage as reasons for the restriction, which has been described as a loss of transparency by developers who work with large language models (LLMs). [21]
In October 2024, researchers at Apple submitted a preprint reporting that LLMs such as o1 may be replicating reasoning steps from the models' own training data. [22] By changing the numbers and names used in a math problem or simply running the same problem again, LLMs would perform somewhat worse than their best benchmark results. Adding extraneous but logically inconsequential information to the problems caused a much greater drop in performance, from −17.5% for o1-preview and −29.1% for o1-mini, to −65.7% for the worst model tested. [23]
Anthropic PBC is an American artificial intelligence (AI) public-benefit startup founded in 2021. It researches and develops AI to "study their safety properties at the technological frontier" and use this research to deploy safe, reliable models for the public. Anthropic has developed a family of large language models (LLMs) named Claude as a competitor to OpenAI's ChatGPT and Google's Gemini.
Braina is a virtual assistant and speech-to-text dictation application for Microsoft Windows developed by Brainasoft. Braina uses natural language interface, speech synthesis, and speech recognition technology to interact with its users and allows them to use natural language sentences to perform various tasks on a computer. The name Braina is a short form of "Brain Artificial".
OpenAI is an American artificial intelligence (AI) research organization founded in December 2015 and headquartered in San Francisco, California. Its stated mission is to develop "safe and beneficial" artificial general intelligence (AGI), which it defines as "highly autonomous systems that outperform humans at most economically valuable work". As a leading organization in the ongoing AI boom, OpenAI is known for the GPT family of large language models, the DALL-E series of text-to-image models, and a text-to-video model named Sora. Its release of ChatGPT in November 2022 has been credited with catalyzing widespread interest in generative AI.
DALL-E, DALL-E 2, and DALL-E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions known as prompts.
GitHub Copilot is a code completion and automatic programming tool developed by GitHub and OpenAI that assists users of Visual Studio Code, Visual Studio, Neovim, and JetBrains integrated development environments (IDEs) by autocompleting code. Currently available by subscription to individual developers and to businesses, the generative artificial intelligence software was first announced by GitHub on 29 June 2021. Users can choose the large language model used for generation.
Prompt engineering is the process of structuring or crafting an instruction in order to produce the best possible output from a generative artificial intelligence (AI) model.
You.com is an AI assistant that began as a personalization-focused search engine. While still offering web search capabilities, You.com has evolved to prioritize a chat-first AI assistant.
ChatGPT is a generative artificial intelligence chatbot developed by OpenAI and launched in 2022. It is currently based on the GPT-4o large language model (LLM). ChatGPT can generate human-like conversational responses and enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. It is credited with accelerating the AI boom, which has led to ongoing rapid investment in and public attention to the field of artificial intelligence (AI). Some observers have raised concern about the potential of ChatGPT and similar programs to displace human intelligence, enable plagiarism, or fuel misinformation.
Generative Pre-trained Transformer 4 (GPT-4) is a multimodal large language model trained and created by OpenAI and the fourth in its series of GPT foundation models. It was launched on March 14, 2023, and made publicly available via the paid chatbot product ChatGPT Plus, via OpenAI's API, and via the free chatbot Microsoft Copilot. As a transformer-based model, GPT-4 uses a paradigm where pre-training using both public data and "data licensed from third-party providers" is used to predict the next token. After this step, the model was then fine-tuned with reinforcement learning feedback from humans and AI for human alignment and policy compliance.
A large language model (LLM) is a type of machine learning model designed for natural language processing tasks such as language generation. LLMs are language models with many parameters, and are trained with self-supervised learning on a vast amount of text.
Microsoft Copilot is a generative artificial intelligence chatbot developed by Microsoft. Based on the GPT-4 series of large language models, it was launched in 2023 as Microsoft's primary replacement for the discontinued Cortana.
In machine learning, the term stochastic parrot is a metaphor to describe the theory that large language models, though able to generate plausible language, do not understand the meaning of the language they process. The term was coined by Emily M. Bender in the 2021 artificial intelligence research paper "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜" by Bender, Timnit Gebru, Angelina McMillan-Major, and Margaret Mitchell.
Grok is a generative artificial intelligence chatbot developed by xAI. Based on the large language model (LLM) of the same name, it was launched in 2023 as an initiative by Elon Musk. The chatbot is advertised as having a "sense of humor" and direct access to X. It is currently available on X, as well as its standalone website and as an iOS, Android app.
Claude is a family of large language models developed by Anthropic. The first model was released in March 2023.
GPT-4o is a multilingual, multimodal generative pre-trained transformer developed by OpenAI and released in May 2024. GPT-4o is free, but ChatGPT Plus subscribers have higher usage limits. It can process and generate text, images and audio. Its application programming interface (API) is faster and cheaper than its predecessor, GPT-4 Turbo.
Apple Intelligence is an artificial intelligence system developed by Apple Inc. Relying on a combination of on-device and server processing, it was announced on June 10, 2024, at WWDC 2024, as a built-in feature of Apple's iOS 18, iPadOS 18, and macOS Sequoia, which were announced alongside Apple Intelligence. Apple Intelligence is free for all users with supported devices. It launched for developers and testers on July 29, 2024, in U.S. English, with the iOS 18.1, macOS 15.1, and iPadOS 18.1 developer betas, released partially in October 2024, and will fully launch by 2025. UK, Australia, Canada, New Zealand, and South African localized versions of English gained support on December 11, 2024, while Chinese, English (India), English (Singapore), French, German, Italian, Japanese, Korean, Portuguese, Spanish, and Vietnamese will be added over the course of 2025. Apple Intelligence is also set to start rolling out in the European Union in April 2025.
DeepSeek is a Chinese artificial intelligence software company. Its first product is an open-source large language model (LLM). It is based in Hangzhou, Zhejiang. It is owned and funded by Chinese hedge fund High-Flyer. Its co-founder, Liang Wenfeng, established the company in 2023 and serves as its CEO.
Qwen is a family of large language models developed by Alibaba Cloud. In July 2024, it was ranked as the top Chinese language model in some benchmarks and third globally behind the top models of Anthropic and OpenAI.
OpenAI o3 is a reflective generative pre-trained transformer (GPT) model developed by OpenAI as a successor to OpenAI o1. It is designed to devote additional deliberation time when addressing questions that require step-by-step logical reasoning.
Reflection, in artificial intelligence, refers to techniques that enable large language models (LLMs) to examine, evaluate, and correct their output. The intermediate output produced may be hidden. By incorporating phases of self‐assessment or internal deliberation, reflective AI aims to improve reasoning accuracy, reduce errors, and enhance interpretability. It is often referred to as "test-time compute".
| Products | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Foundation models | |||||||||
| People |
| ||||||||
| Related | |||||||||
| Concepts |
| ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Models |
| ||||||||
| Companies | |||||||||
