AI Safety Institute Launches, Leading Companies Join Consortium

The Biden administration officially named a top White House aide as the director of the newly established safety institute for artificial intelligence.

Elizabeth Kelly will lead the AI Safety Institute at the National Institute for Standards and Technology, which will be part of the Commerce Department.

Currently an economic policy adviser for President Joe Biden, Kelly played an integral role in drafting the executive order signed at the end of October that established the institute, the Commerce Department said in a statement.

Already several top companies in the AI space are pledging their involvement, joining a new safety consortium to play a part in supporting the safe development of generative AI.  

MongoDB, Inc. announced that it is a founding member of the U.S. Artificial Intelligence Safety Institute Consortium (AISIC), a coalition focusing on the safe development and deployment of generative AI. Microsoft, Alphabet’s Google, Apple, Facebook-parent Meta Platforms, OpenAI, and others have also joined.

Leaders from industry, government, academia, and non-profit organizations participating in the consortium will work together with NIST to support its efforts to create safe and trustworthy artificial intelligence (AI).

The consortium will focus on the most advanced AI systems, such as state-of-the-art foundation models, to assess the risk and impact of current and next-generation AI technology on individuals and society.

By defining a new measurement science to identify proven, scalable, and interoperable techniques and metrics for testing and verifying the impact of AI systems, the consortium will create standards and guidelines that promote the development and responsible use of AI.

“We believe that technology driven by software and data makes the world a better place, and we see our customers building modern applications achieving that every day,” said Lena Smart, chief information security officer at MongoDB. “New technology like generative AI can have an immense benefit to society, but we must ensure AI systems are built and deployed using standards that help ensure they operate safely and without harm across populations. By supporting the U.S. Artificial Intelligence Safety Institute Consortium as a founding member, MongoDB’s goal is to use scientific rigor, our industry expertise, and a human-centered approach to guide organizations on safely testing and deploying trustworthy AI systems without stifling innovation.”

The newly formed consortium also includes government agencies, academic institutions and other companies like Northrop Grumman, BP, Qualcomm and Mastercard.

The new institute will play a critical role in fostering the development of the technology. By July, it’s set to create “red team” testing standards for major AI developers to ensure that the systems are safe for consumers and businesses.

The administration considers the safety tests as necessary to unlock the benefits of the rapidly moving technology, creating a level of trust that will allow for wider adoption of AI.

The federal government recently began requiring AI companies to test their systems. But so far, those tests lack the universal set of standards that the institute plans to finalize this summer.

“The U.S. government has a significant role to play in setting the standards and developing the tools we need to mitigate the risks and harness the immense potential of artificial intelligence. President Biden directed us to pull every lever to accomplish two key goals: set safety standards and protect our innovation ecosystem. That’s precisely what the U.S. AI Safety Institute Consortium is set up to help us do,” said Secretary of U.S. Department of Commerce Gina Raimondo. “Through President Biden’s landmark Executive Order, we will ensure America is at the front of the pack—and by working with this group of leaders from industry, civil society, and academia, together we can confront these challenges to develop the measurements and standards we need to maintain America’s competitive edge and develop AI responsibly.”

Additional information about the AISIC can be found on the consortium website.