Improving Verifiability in AI Development: Multi-Stakeholder Report
OpenAI contributed to a multi-stakeholder report co-authored by 58 researchers across 30 organizations, including Mila, CSET, and the Schwartz Reisman Institute. The report identifies 10 mechanisms for improving the verifiability of claims about AI systems. These tools are intended to help developers demonstrate safety, security, fairness, and privacy properties, while enabling policymakers and civil society to evaluate AI development processes.
Related guides (3)
Related events (8)
OpenAI Expands External Safety Testing Ecosystem
OpenAI published a post describing its use of independent experts to evaluate frontier AI systems through third-party testing. The initiative aims to strengthen safety validation, verify safeguards, and increase transparency around capability and risk assessments. The announcement signals a continued push toward external accountability mechanisms for frontier model evaluation.
Moving AI Governance Forward: OpenAI and Leading Labs Make Voluntary Safety Commitments
OpenAI and other leading AI laboratories announced voluntary commitments aimed at reinforcing AI safety, security, and trustworthiness. The commitments represent a coordinated industry response to governance concerns ahead of anticipated regulatory action. This move signals alignment among frontier labs on baseline safety standards, though the voluntary nature leaves enforcement questions open.
AI Safety via Debate
OpenAI proposes a safety technique in which two AI agents debate a topic and a human judge determines the winner, with the goal of making it easier for humans to supervise AI systems that may be more capable than themselves. The core intuition is that it is easier to verify a correct argument than to generate one, so a dishonest agent can be caught by an honest opponent. The paper introduces debate as a scalable oversight mechanism applicable to complex tasks where direct human evaluation is infeasible.
A shared playbook for trustworthy third party evaluations
OpenAI has published guidance outlining a shared framework for conducting trustworthy third-party evaluations of frontier AI systems. The playbook covers methodology for assessing model capabilities, safeguards, and evaluation validity. This represents OpenAI's attempt to standardize and legitimize external auditing practices for frontier models.
OpenAI Reports Progress with US CAISI and UK AISI on AI Safety and Security
OpenAI has published an update on its ongoing partnership with the US Cyber and AI Safety Institute (CAISI) and the UK AI Safety Institute (AISI). The collaboration focuses on strengthening AI safety and security practices. The announcement signals continued institutional engagement between OpenAI and government AI safety bodies in both countries.
OpenAI Policy Paper: Four Strategies for Industry Cooperation on AI Safety
OpenAI published a policy research paper identifying four strategies to foster long-term industry cooperation on AI safety norms: communicating risks and benefits, technical collaboration, increased transparency, and incentivizing standards. The paper argues that competitive pressures risk creating a collective action problem where AI companies under-invest in safety. The analysis frames industry-wide coordination as essential to ensuring AI systems are safe and beneficial.
Concrete Problems in AI Safety
OpenAI, Google Brain, Berkeley, and Stanford researchers co-authored 'Concrete Problems in AI Safety,' a foundational paper exploring research challenges in ensuring modern ML systems operate as intended. The paper identifies and frames specific technical safety problems for the field. Published in June 2016, it became a landmark reference for AI safety research agendas.
Preparing for malicious uses of AI
OpenAI co-authored a multi-institutional paper forecasting how malicious actors could misuse AI technology, produced in collaboration with FHI, CSER, CNAS, EFF, and others over nearly a year. The paper outlines potential threat vectors and proposes prevention and mitigation strategies. This represents an early coordinated effort among AI safety and policy organizations to systematically address AI misuse risks.