Announced in 2016, Gym is an open-source Python library designed to assist in the advancement of reinforcement learning algorithms. It aimed to standardize how environments are specified in AI research study, making released research more quickly reproducible [24] [144] while supplying users with a basic interface for engaging with these environments. In 2022, brand-new advancements of Gym have been relocated to the library Gymnasium. [145] [146]
Gym Retro

Released in 2018, Gym Retro is a platform for reinforcement knowing (RL) research on computer game [147] using RL algorithms and research study generalization. Prior RL research study focused mainly on enhancing representatives to fix single jobs. Gym Retro provides the ability to generalize between games with comparable concepts however different appearances.

RoboSumo

Released in 2017, RoboSumo is a virtual world where humanoid metalearning robotic agents initially lack knowledge of how to even walk, however are given the objectives of learning to move and to push the opposing agent out of the ring. [148] Through this adversarial knowing process, the agents find out how to adapt to altering conditions. When an agent is then removed from this virtual environment and placed in a new virtual environment with high winds, the agent braces to remain upright, suggesting it had actually discovered how to stabilize in a generalized way. [148] [149] OpenAI's Igor Mordatch argued that competitors in between agents could produce an intelligence "arms race" that could increase an agent's ability to function even outside the context of the competition. [148]
OpenAI 5

OpenAI Five is a group of five OpenAI-curated bots used in the competitive five-on-five computer game Dota 2, that learn to play against human players at a high ability level entirely through experimental algorithms. Before becoming a group of 5, the first public presentation occurred at The International 2017, the annual premiere champion competition for the game, where Dendi, a professional Ukrainian gamer, lost against a bot in a live individually matchup. [150] [151] After the match, CTO Greg Brockman explained that the bot had actually learned by playing against itself for two weeks of genuine time, and that the learning software was a step in the instructions of producing software application that can deal with complicated jobs like a cosmetic surgeon. [152] [153] The system uses a form of support knowing, as the bots find out gradually by playing against themselves hundreds of times a day for months, and are rewarded for actions such as killing an enemy and taking map goals. [154] [155] [156]
By June 2018, the ability of the bots expanded to play together as a full team of 5, and they were able to defeat teams of amateur and semi-professional gamers. [157] [154] [158] [159] At The International 2018, OpenAI Five played in two exhibition matches against professional gamers, but ended up losing both video games. [160] [161] [162] In April 2019, OpenAI Five beat OG, the ruling world champions of the video game at the time, 2:0 in a live exhibit match in San Francisco. [163] [164] The bots' final public look came later that month, where they played in 42,729 overall games in a four-day open online competitors, winning 99.4% of those games. [165]
OpenAI 5's systems in Dota 2's bot gamer shows the obstacles of AI systems in multiplayer online battle arena (MOBA) games and how OpenAI Five has actually shown making use of deep reinforcement knowing (DRL) representatives to attain superhuman proficiency in Dota 2 matches. [166]
Dactyl

Developed in 2018, Dactyl utilizes machine learning to train a Shadow Hand, a human-like robot hand, to control physical objects. [167] It discovers totally in simulation utilizing the very same RL algorithms and training code as OpenAI Five. OpenAI tackled the things orientation issue by utilizing domain randomization, a simulation technique which exposes the student to a range of experiences rather than attempting to fit to reality. The set-up for Dactyl, aside from having motion tracking electronic cameras, also has RGB cameras to allow the robot to manipulate an arbitrary things by seeing it. In 2018, OpenAI revealed that the system was able to manipulate a cube and an octagonal prism. [168]
In 2019, OpenAI demonstrated that Dactyl could resolve a Rubik's Cube. The robotic was able to fix the puzzle 60% of the time. Objects like the Rubik's Cube introduce intricate physics that is harder to design. OpenAI did this by improving the toughness of Dactyl to perturbations by utilizing Automatic Domain Randomization (ADR), a simulation approach of producing progressively harder environments. ADR varies from manual domain randomization by not requiring a human to specify randomization ranges. [169]
API

In June 2020, OpenAI announced a multi-purpose API which it said was "for accessing new AI models developed by OpenAI" to let developers call on it for "any English language AI job". [170] [171]
Text generation

The company has actually popularized generative pretrained transformers (GPT). [172]
OpenAI's initial GPT design ("GPT-1")

The initial paper on generative pre-training of a transformer-based language design was written by Alec Radford and his coworkers, and bytes-the-dust.com released in preprint on OpenAI's site on June 11, 2018. [173] It demonstrated how a generative model of language could obtain world understanding and procedure long-range dependences by pre-training on a diverse corpus with long stretches of contiguous text.

GPT-2

Generative Pre-trained Transformer 2 ("GPT-2") is an unsupervised transformer language model and the successor to OpenAI's initial GPT model ("GPT-1"). GPT-2 was revealed in February 2019, with just minimal demonstrative versions at first launched to the general public. The full version of GPT-2 was not immediately released due to concern about possible abuse, consisting of applications for writing phony news. [174] Some experts revealed uncertainty that GPT-2 posed a considerable threat.

In action to GPT-2, the Allen Institute for Artificial Intelligence responded with a tool to identify "neural fake news". [175] Other scientists, such as Jeremy Howard, warned of "the innovation to completely fill Twitter, email, and the web up with reasonable-sounding, context-appropriate prose, which would drown out all other speech and be impossible to filter". [176] In November 2019, OpenAI released the complete variation of the GPT-2 language design. [177] Several websites host interactive presentations of various instances of GPT-2 and other transformer models. [178] [179] [180]
GPT-2's authors argue without supervision language models to be general-purpose learners, illustrated by GPT-2 attaining advanced accuracy and perplexity on 7 of 8 zero-shot jobs (i.e. the design was not further trained on any task-specific input-output examples).

The corpus it was trained on, called WebText, contains slightly 40 gigabytes of text from URLs shared in with at least 3 upvotes. It avoids certain problems encoding vocabulary with word tokens by utilizing byte pair encoding. This permits representing any string of characters by encoding both specific characters and multiple-character tokens. [181]
GPT-3

First explained in May 2020, Generative Pre-trained [a] Transformer 3 (GPT-3) is a without supervision transformer language model and the successor to GPT-2. [182] [183] [184] OpenAI specified that the full version of GPT-3 contained 175 billion criteria, [184] two orders of magnitude bigger than the 1.5 billion [185] in the complete version of GPT-2 (although GPT-3 designs with as couple of as 125 million parameters were likewise trained). [186]
OpenAI stated that GPT-3 prospered at certain "meta-learning" tasks and might generalize the purpose of a single input-output pair. The GPT-3 release paper gave examples of translation and cross-linguistic transfer knowing in between English and Romanian, and between English and German. [184]
GPT-3 drastically enhanced benchmark outcomes over GPT-2. OpenAI cautioned that such scaling-up of language models could be approaching or experiencing the essential ability constraints of predictive language models. [187] Pre-training GPT-3 required several thousand petaflop/s-days [b] of compute, compared to tens of petaflop/s-days for the complete GPT-2 design. [184] Like its predecessor, [174] the GPT-3 trained model was not right away released to the general public for concerns of possible abuse, although OpenAI planned to allow gain access to through a paid cloud API after a two-month complimentary private beta that started in June 2020. [170] [189]
On September 23, 2020, GPT-3 was licensed specifically to Microsoft. [190] [191]
Codex

Announced in mid-2021, Codex is a descendant of GPT-3 that has actually furthermore been trained on code from 54 million GitHub repositories, [192] [193] and is the AI powering the code autocompletion tool GitHub Copilot. [193] In August 2021, an API was released in personal beta. [194] According to OpenAI, the design can develop working code in over a dozen programs languages, most efficiently in Python. [192]
Several issues with glitches, style flaws and security vulnerabilities were pointed out. [195] [196]
GitHub Copilot has actually been implicated of producing copyrighted code, with no author attribution or license. [197]
OpenAI announced that they would stop assistance for Codex API on March 23, 2023. [198]
GPT-4

On March 14, 2023, OpenAI revealed the release of Generative Pre-trained Transformer 4 (GPT-4), capable of accepting text or image inputs. [199] They announced that the upgraded technology passed a simulated law school bar examination with a score around the leading 10% of test takers. (By contrast, GPT-3.5 scored around the bottom 10%.) They said that GPT-4 might likewise read, evaluate or generate as much as 25,000 words of text, and write code in all significant programs languages. [200]
Observers reported that the version of ChatGPT utilizing GPT-4 was an enhancement on the previous GPT-3.5-based version, with the caveat that GPT-4 retained a few of the problems with earlier modifications. [201] GPT-4 is also capable of taking images as input on ChatGPT. [202] OpenAI has declined to reveal various technical details and statistics about GPT-4, such as the accurate size of the design. [203]
GPT-4o

On May 13, 2024, bytes-the-dust.com OpenAI revealed and launched GPT-4o, which can process and generate text, images and audio. [204] GPT-4o attained cutting edge lead to voice, multilingual, and vision standards, setting brand-new records in audio speech recognition and translation. [205] [206] It scored 88.7% on the Massive Multitask Language Understanding (MMLU) criteria compared to 86.5% by GPT-4. [207]
On July 18, 2024, OpenAI released GPT-4o mini, a smaller sized variation of GPT-4o replacing GPT-3.5 Turbo on the ChatGPT user interface. Its API costs $0.15 per million input tokens and $0.60 per million output tokens, compared to $5 and $15 respectively for GPT-4o. OpenAI anticipates it to be particularly beneficial for enterprises, start-ups and designers seeking to automate services with AI representatives. [208]
o1

On September 12, 2024, OpenAI released the o1-preview and o1-mini designs, which have actually been designed to take more time to think about their actions, resulting in greater precision. These designs are especially reliable in science, coding, and thinking tasks, and were made available to ChatGPT Plus and Staff member. [209] [210] In December 2024, o1-preview was changed by o1. [211]
o3

On December 20, 2024, OpenAI unveiled o3, the successor of the o1 reasoning design. OpenAI likewise revealed o3-mini, a lighter and faster version of OpenAI o3. As of December 21, 2024, this model is not available for public use. According to OpenAI, they are evaluating o3 and o3-mini. [212] [213] Until January 10, 2025, security and security researchers had the opportunity to obtain early access to these models. [214] The design is called o3 rather than o2 to avoid confusion with telecommunications companies O2. [215]
Deep research

Deep research is an agent established by OpenAI, unveiled on February 2, 2025. It leverages the abilities of OpenAI's o3 model to perform extensive web browsing, data analysis, and synthesis, systemcheck-wiki.de providing detailed reports within a timeframe of 5 to thirty minutes. [216] With searching and Python tools enabled, it reached an accuracy of 26.6 percent on HLE (Humanity's Last Exam) benchmark. [120]
Image category

CLIP

Revealed in 2021, CLIP (Contrastive Language-Image Pre-training) is a model that is trained to analyze the semantic resemblance between text and images. It can notably be used for image category. [217]
Text-to-image

DALL-E

Revealed in 2021, DALL-E is a Transformer design that develops images from textual descriptions. [218] DALL-E uses a 12-billion-parameter version of GPT-3 to translate natural language inputs (such as "a green leather handbag formed like a pentagon" or "an isometric view of an unfortunate capybara") and create matching images. It can produce images of practical things ("a stained-glass window with a picture of a blue strawberry") in addition to objects that do not exist in truth ("a cube with the texture of a porcupine"). Since March 2021, no API or code is available.

DALL-E 2

In April 2022, OpenAI announced DALL-E 2, an upgraded version of the design with more reasonable results. [219] In December 2022, OpenAI published on GitHub software application for Point-E, a new basic system for transforming a text description into a 3-dimensional model. [220]
DALL-E 3

In September 2023, OpenAI announced DALL-E 3, a more effective model better able to generate images from complicated descriptions without manual timely engineering and render intricate details like hands and text. [221] It was released to the public as a ChatGPT Plus function in October. [222]
Text-to-video

Sora

Sora is a text-to-video model that can produce videos based on short detailed prompts [223] as well as extend existing videos forwards or in reverse in time. [224] It can produce videos with resolution approximately 1920x1080 or 1080x1920. The maximal length of produced videos is unidentified.

Sora's advancement team named it after the Japanese word for "sky", to represent its "limitless imaginative capacity". [223] Sora's innovation is an adaptation of the innovation behind the DALL · E 3 text-to-image design. [225] OpenAI trained the system using publicly-available videos along with copyrighted videos licensed for that purpose, however did not expose the number or the precise sources of the videos. [223]
OpenAI showed some Sora-created high-definition videos to the public on February 15, 2024, stating that it might generate videos as much as one minute long. It likewise shared a technical report highlighting the methods used to train the model, and the model's abilities. [225] It acknowledged some of its shortcomings, including struggles replicating complicated physics. [226] Will Douglas Heaven of the MIT Technology Review called the demonstration videos "remarkable", but kept in mind that they must have been cherry-picked and may not represent Sora's typical output. [225]
Despite uncertainty from some academic leaders following Sora's public demo, significant entertainment-industry figures have actually shown significant interest in the technology's capacity. In an interview, actor/filmmaker Tyler Perry revealed his awe at the innovation's ability to create realistic video from text descriptions, mentioning its prospective to transform storytelling and content production. He said that his enjoyment about Sora's possibilities was so strong that he had actually chosen to stop briefly prepare for expanding his Atlanta-based movie studio. [227]
Speech-to-text

Whisper

Released in 2022, Whisper is a general-purpose speech recognition design. [228] It is trained on a large dataset of varied audio and is also a multi-task design that can carry out multilingual speech recognition along with speech translation and language recognition. [229]
Music generation

MuseNet

Released in 2019, MuseNet is a deep neural net trained to anticipate subsequent musical notes in MIDI music files. It can generate songs with 10 instruments in 15 designs. According to The Verge, a song generated by MuseNet tends to begin fairly but then fall into chaos the longer it plays. [230] [231] In pop culture, preliminary applications of this tool were used as early as 2020 for the web mental thriller Ben Drowned to produce music for the titular character. [232] [233]
Jukebox

Released in 2020, Jukebox is an open-sourced algorithm to create music with vocals. After training on 1.2 million samples, the system accepts a genre, artist, and a snippet of lyrics and outputs song samples. OpenAI mentioned the tunes "show local musical coherence [and] follow standard chord patterns" however acknowledged that the tunes lack "familiar bigger musical structures such as choruses that duplicate" and that "there is a considerable space" in between Jukebox and human-generated music. The Verge stated "It's technologically remarkable, even if the results seem like mushy versions of tunes that might feel familiar", while Business Insider stated "surprisingly, some of the resulting songs are appealing and sound legitimate". [234] [235] [236]
Interface

Debate Game

In 2018, OpenAI released the Debate Game, which teaches makers to discuss toy problems in front of a human judge. The purpose is to research whether such a technique may help in auditing AI choices and in developing explainable AI. [237] [238]
Microscope

Released in 2020, Microscope [239] is a collection of visualizations of every considerable layer and neuron of 8 neural network designs which are typically studied in interpretability. [240] Microscope was developed to analyze the functions that form inside these neural networks easily. The models included are AlexNet, VGG-19, various versions of Inception, and different versions of CLIP Resnet. [241]
ChatGPT

Launched in November 2022, ChatGPT is a synthetic intelligence tool constructed on top of GPT-3 that provides a conversational interface that permits users to ask concerns in natural language. The system then reacts with a response within seconds.