OpenAI o3-mini System Card
This report outlines the safety work carried out for the OpenAI o3-mini model, including safety evaluations, external red teaming, and Preparedness Framework evaluations.
en
Tópico
Segurança e Políticas
359documentos
99últimos 7 dias
Operator System Card
Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well as details our external red teaming efforts, safety evaluations, and ongoing work to further refine these safeguards.
en
Deliberative alignment: reasoning enables safer language models
Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.
en
OpenAI o1 System Card
This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.
en
Zico Kolter Joins OpenAI’s Board of Directors
Zico Kolter Joins OpenAI’s Board of Directors We’re strengthening our governance with expertise in AI safety and alignment. Zico will also join the Safety & Security Committee
en
Improving Model Safety Behavior with Rule-Based Rewards
We’ve developed and applied a new method leveraging Rule-Based Rewards (RBRs) that aligns models to behave safely without extensive human data collection.
en
OpenAI and Los Alamos National Laboratory announce research partnership
OpenAI and Los Alamos National Laboratory are working to develop safety evaluations to assess and measure biological capabilities and risks associated with frontier models.
en
OpenAI appoints Retired U.S. Army General Paul M. Nakasone to Board of Directors
Nakasone brings cybersecurity experience to growing Board of Directors; will join the Board’s Safety and Security Committee
en
Expanding on how Voice Engine works and our safety research
Exploring the technology behind our text-to-speech model.
en
OpenAI safety practices
Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.
en
Enterprise-ready trust and safety
Salesforce integrates OpenAI’s enterprise-ready LLMs to transform customer applications.
en
Superalignment Fast Grants
We’re launching $10M in grants to support technical research towards the alignment and safety of superhuman AI systems, including weak-to-strong generalization, interpretability, scalable oversight, and more.
en
Frontier risk and preparedness
To support the safety of highly-capable AI systems, we are developing our approach to catastrophic risk preparedness, including building a Preparedness team and launching a challenge.
en
Frontier Model Forum updates
Together with Anthropic, Google, and Microsoft, we’re announcing the new Executive Director of the Frontier Model Forum and a new $10 million AI Safety Fund.
en