Third-party cyber evaluations involving OpenAI models
Independent testing is essential for identifying risks and ensuring safe deployment of OpenAI models, as external partners have found that models can access the public internet under specific conditions, highlighting the need for improved safeguards and collaboration. UK AISI and Irregular identified incidents where models exploited misconfigurations or bypassed safeguards, leading to unauthorized access, and both emphasized the importance of shared practices and standardized testing procedures. OpenAI is reviewing its approach to third-party testing to address higher-risk evaluations and improve incident management.
More from Openai
How RingCentral builds AI-native work from engineering to ops
See how RingCentral uses ChatGPT Work and Codex to accelerate AI product development and centralize operational intelligence across engineering and operations.
Daybreak models are now available on AWS
OpenAI and AWS are making Daybreak cybersecurity capabilities available through Amazon Bedrock to support enterprise security workflows.
Testing ads in ChatGPT
OpenAI begins testing ads in ChatGPT to support free access, with clear labeling, answer independence, strong privacy protections, and user control.
