OpenAI Company Brief
Founded in 2015 by several AI visionaries including Elon Musk and now-CEO Sam Altman, OpenAI is committed to the audacious goal of “building safe and beneficial artificial general intelligence [AGI] for the benefit of humanity.” OpenAI gained widespread, even worldwide, attention in November 2022 with the release of ChatGPT, a generative AI application capable of creating, virtually instantaneously, a variety of original written content including essays, reports, and even computer code, all in response to simple user requests.
Fast Facts
OpenAI
3180 18th Street
San Francisco, CA 94110
Web: https://www.openai.com/
Type of Vendor: Artificial Intelligence System Provider
Founded: 2015
Service Areas: Worldwide
Profile
Founded in 2015 by several AI visionaries including Elon Musk and now-CEO Sam Altman, OpenAI is committed to the audacious goal of “building safe and beneficial artificial general intelligence [AGI] for the benefit of humanity.”
AGI, which is characterized as having human-like cognitive capabilities, is both exciting as a vehicle for augmenting human intelligence, and scary as a force which could replace, even enslave, its human masters. Aware of this dilemma, in April 2018, the company published its OpenAI Charter:
“OpenAI’s mission is to ensure that artificial general intelligence (AGI) – by which we mean highly autonomous systems that outperform humans at most economically valuable work – benefits all of humanity. We will attempt to directly build safe and beneficial AGI, but will also consider our mission fulfilled if our work aids others to achieve this outcome.
“We commit to use any influence we obtain over AGI’s deployment to ensure it is used for the benefit of all, and to avoid enabling uses of AI or AGI that harm humanity or unduly concentrate power.
“We are committed to doing the research required to make AGI safe, and to driving the broad adoption of such research across the AI community.”
From Non-Profit to Profit
Early on, the management of OpenAI realized that “donations alone would not scale with the cost of computational power and talent required to push core research forward, jeopardizing [the company’s] mission.”
Consequently, they devised a structure in which the OpenAI Nonprofit would continue to exist but a new for-profit subsidiary would be formed, attracting the requisite venture and other investment. As reported by CB Information Services, OpenAI has raised $14.3 billion over nine rounds of funding, with the latest contribution being $300 million in April 2023. The company’s 2022 revenue was estimated at $20 million to $30 million.
As revealed by Global Business Outlook, “In 2023, OpenAI expects to earn $200 million in income. As an illustration of how it generates revenue, it costs 6 cents to process 1,000 tokens of prompts in its GPT-4 model, and offers a $20/month subscription tier for ChatGPT.”1
Throughout the nonprofit-to-profit business transition, OpenAI has maintained that “the for-profit would be legally bound to pursue the Nonprofit’s mission.” In fact, the for-profit “is fully controlled by the OpenAI Nonprofit.”
The Microsoft Connection
In July 2019, OpenAI began a lucrative partnership with Microsoft “to further extend Microsoft Azure’s capabilities in large-scale AI systems.” As part of the arrangement, the two companies agreed that:
- “Microsoft and OpenAI will jointly build new Azure AI supercomputing technologies.
- “OpenAI will port its services to run on Microsoft Azure, which it will use to create new AI technologies and deliver on the promise of artificial general intelligence.
- “Microsoft will become OpenAI’s preferred partner for commercializing new AI technologies.”
The ChatGPT Phenomenon
OpenAI gained widespread, even worldwide, attention in November 2022 with the release of ChatGPT, a “generative AI” application capable of creating, virtually instantaneously, a variety of “original” written content, including essays, reports, even computer code, all in response to simple user requests.
As a program that can write better than the vast majority of humans, that can churn out text just by sifting through massive amounts of training data, and can satisfy enterprise writing assignments from sales and marketing pitches to the production of annual reports, ChatGPT has been quickly adopted by enterprise managers and staff, plus anyone else who finds the formation of written communications either onerous or particularly challenging.
While some problems persist – notably, the tendency of generative AI programs to make things up (called “hallucinations”), and the need for fresh training data to produce accurate and timely text – ChatGPT and its successors will continue to power OpenAI’s commercial and non-commercial ambitions.
As an example of ChatGPT in action, consider the following request and response.
Request: Tell me about OpenAI, its history, leadership, products, and competitors.
Response: OpenAI is an artificial intelligence research organization that aims to ensure that artificial general intelligence (AGI) benefits all of humanity. It was founded in December 2015 by Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, John Schulman, and Wojciech Zaremba. OpenAI’s primary focus is on the development of advanced AI technologies while ensuring their safe and ethical deployment.
The organization has a rich history of groundbreaking research and innovation in the field of artificial intelligence. Initially, OpenAI focused on advancing the field through publishing research papers and open-sourcing their AI frameworks and tools. However, in 2018, the organization shifted its strategy towards a more cooperative and safety-conscious approach due to concerns about AGI’s potential risks.
OpenAI has a talented team of researchers, engineers, and experts in various AI-related disciplines. While the specific leadership structure might have changed since my knowledge cutoff in September 2021, at that time, the leaders of OpenAI included Sam Altman as the CEO, Greg Brockman as the President, Ilya Sutskever as the Chief Scientist, and Wojciech Zaremba as a research scientist.
OpenAI has developed and released several notable products and projects. One of their most famous creations is GPT-3 (Generative Pre-trained Transformer 3), which is a state-of-the-art language model capable of generating human-like text. GPT-3 has garnered significant attention for its ability to perform various natural language processing tasks, including text completion, translation, summarization, and more.
In addition to GPT-3, OpenAI has worked on reinforcement learning algorithms and models, robotics projects, and other AI-related research initiatives. They have also collaborated with external organizations and researchers to advance the field and promote cooperation.
OpenAI faces competition from various organizations and companies in the AI space. Some of its notable competitors include DeepMind, a subsidiary of Alphabet Inc., which has made significant advancements in areas like reinforcement learning and game-playing AI. Other major players in the AI field, such as Microsoft, Google, Facebook, and Amazon, also have their AI research divisions and are actively investing in AI technologies. The competition in the AI industry is fierce, with multiple organizations striving to push the boundaries of AI research and development.
OpenAI’s Safety Obsession
Whether motivated by a self-serving desire to avoid future litigation or a selfless desire to warn the world about the potential danger of artificial intelligence, OpenAI is fully engaged in promoting and delivering AGI safety and security. Witness the following:
- Compliance – “OpenAI complies with GDPR and CCPA. The OpenAI API has been evaluated by a third-party security auditor and is SOC 2 Type 2 compliant.”
- External Auditing – “The OpenAI API undergoes annual third-party penetration testing, which identifies security weaknesses before they can be exploited by malicious actors.”
- Customer Requirements – “OpenAI has experience helping our customers meet their regulatory, industry and contractual requirements (e.g., HIPAA).”
- Reporting Security Issues – “OpenAI invites security researchers, ethical hackers, and technology enthusiasts to report security issues via our Bug Bounty Program.”
Key Executives
- Sam Altman, Chief Executive Officer
- Greg Brockman, Chairman & President
- Brad Lightcap, Chief Operating Officer
- Mira Murati, Chief Technology Officer
- Ilya Sutskever, Chief Scientist
- Chris Clark, Head of Nonprofit and Strategic Initiatives
Major Products
ChatGPT
OpenAI’s signature product, ChatGPT is a generative AI application capable of creating, virtually instantaneously, a variety of “original” written content, including essays, reports, even computer code, all in response to simple user requests. Or as OpenAI invites us, “Get instant answers, find creative inspiration, and learn something new.”
GPT-4
GPT-4 is OpenAI’s most advanced system; it “can generate, edit, and iterate with users on creative and technical writing tasks, such as composing songs, writing screenplays, or learning a user’s writing style.”
DALL-E 2
DALL-E 2 “can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles.” See Figure 1 for a sample image.
Figure 1. An astronaut riding a horse in photorealistic style
Source: OpenAIWhisper
Whisper is an automatic speech recognition (ASR) system “that can transcribe, identify, and translate multiple languages. Whisper was trained on 680,000 hours of multilingual and multitask supervised data collected from the web.”
Major Competitors
Recent Activity
June 1, 2023 – Cybersecurity Grant Program – OpenAI launched “the Cybersecurity Grant Program – a $1M initiative to boost and quantify AI-powered cybersecurity capabilities and to foster high-level AI and cybersecurity discourse.” The company’s “goal is to work with defenders across the globe to change the power dynamics of cybersecurity through the application of AI and the coordination of like-minded individuals working for our collective safety.”
May 25, 2023 – Democratic Inputs to AI – OpenAI launched “a program to award ten $100,000 grants to fund experiments in setting up a democratic process for deciding what rules AI systems should follow, within the bounds defined by the law.”
April 11, 2023 – Bug Bounty Program – “To incentivize testing and as a token of [the company’s] appreciation, [OpenAI] will be offering cash rewards based on the severity and impact of the reported issues. Rewards range from $200 for low-severity findings to up to $20,000 for exceptional discoveries.”
January 23, 2023 – OpenAI and Microsoft Extend Partnership – “OpenAI and Microsoft [extend their] partnership. This multi-year, multi-billion dollar investment from Microsoft follows their previous investments in 2019 and 2021, and will allow [OpenAI] to continue [its] independent research and develop AI that is increasingly safe, useful, and powerful.”
November 30, 2022 – Introducing ChatGPT – OpenAI has “trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests.”
References
1 “Exploring the Alternatives to OpenAI.” Global Business Outlook. June 30, 2023.