OpenAI publishes a report on mechanisms to improve verifiability in AI development, addressing how stakeholders can verify organizations' claims about AI system properties and safety practices.
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.
# Improving verifiability in AI development
Source: [https://openai.com/index/improving-verifiability/](https://openai.com/index/improving-verifiability/)
While a growing number of organizations have articulated ethics principles to guide their AI development process, it can be difficult for those outside of an organization to verify whether the organization’s AI systems reflect those principles in practice\. This ambiguity makes it harder for stakeholders such as users, policymakers, and civil society to scrutinize AI developers’ claims about properties of AI systems and could fuel competitive corner\-cutting, increasing social risks and harms\. The report describes existing and potential mechanisms that can help stakeholders grapple with questions like:
- Can I \(as a user\) verify the claims made about the level of privacy protection guaranteed by a new AI system I’d like to use for machine translation of sensitive documents?
- Can I \(as a regulator\) trace the steps that led to an accident caused by an autonomous vehicle? Against what standards should an autonomous vehicle company’s safety claims be compared?
- Can I \(as an academic\) conduct impartial research on the risks associated with large\-scale AI systems when I lack the computing resources of industry?
- Can I \(as an AI developer\) verify that my competitors in a given area of AI development will follow best practices rather than cut corners to gain an advantage?
The 10 mechanisms highlighted in the report are listed below, along with recommendations aimed at advancing each one\. \(See the[report\(opens in a new window\)](https://arxiv.org/abs/2004.07213)for discussion of how these mechanisms support verifiable claims as well as relevant caveats about our findings\.\)
OpenAI publishes a policy research paper identifying four strategies to improve industry cooperation on AI safety norms: communicating risks/benefits, technical collaboration, increased transparency, and incentivizing standards. The analysis addresses how competitive pressures could lead to under-investment in safety and proposes mechanisms to align incentives toward safe AI development.
OpenAI outlines 10 safety practices it actively uses and improves upon, including empirical red-teaming, alignment research, abuse monitoring, and voluntary commitments shared at the AI Seoul Summit. The company emphasizes a balanced, scientific approach to safety integrated into development from the outset.
OpenAI outlines its comprehensive approach to AI safety, emphasizing rigorous testing, iterative deployment, real-world monitoring, and regulatory engagement to ensure powerful AI systems are built and used safely.
OpenAI publishes AI governance recommendations committing companies to internal and external red-teaming for safety risks, information sharing on emerging capabilities, and mechanisms for detecting AI-generated audio and visual content.
OpenAI announces a strengthened safety ecosystem through external third-party testing and evaluations of frontier AI models, including independent assessments, methodology reviews, and subject-matter expert probing. The company commits to transparency by publicly sharing third-party assessment results and supporting independent evaluations since GPT-4's launch.