Improving verifiability in AI development
OpenAI Blog
A consortium of 58 researchers across 30 organizations published a report outlining 10 mechanisms to improve verification of claims about AI system safety, security, fairness, and privacy. The report involves institutions including the Centre for the Future of Intelligence, Mila, and the Center for Security and Emerging Technology. The mechanisms provide tools for developers to demonstrate AI system properties and for policymakers, users, and civil society to evaluate AI development practices.
Why it matters
We’ve contributed to a multi-stakeholder report by 58 co-authors at 30 organizations, including the Centre for the Future of Intelligence, Mila, Schwartz Reisman Institute for Technology and Society, Center for Advanced Study in the Behavioral Sciences, and Center for Security and Emerging Technologies. This report describes 10 mechanisms to improve the verifiability of claims made about AI systems. Developers can use these tools to provide evidence that AI systems are safe, secure, fair, or privacy-preserving. Users, policymakers, and civil society can use these tools to evaluate AI development processes.