Third-party cyber evaluations involving OpenAI models

OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.

From the source
OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.
openai.com

Visit source ↗openai.com

Around this story

Simon Willisonreported

Other stories

OpenAI · 28 AugOur decision on Cursor following its acquisition by SpaceX

OpenAI · 28 AugSupporting Thailand’s next generation of AI startupsPartnership

OpenAI · 27 AugBetter answers, broader thinking: What students gain from ChatGPT and critical-thinking trainingResearch paper

OpenAI · 27 AugExpanding OpenAI’s presence in BrazilAvailability change

23 days ago

Third-party cyber evaluations involving OpenAI models

reported

23 days ago

Announced: 04 Aug 2026 19:00 UTC
Detected: 04 Aug 2026 21:04 UTC (+2h after)

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update