OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI browser agents. The update adds an adversarially trained model plus stronger ...

As AI is embedded inside systems, teams must design APIs with governance, observability and scalability in mind.

OpenAI has begun accepting submissions from third-party developers for their apps to be accessible directly in ChatGPT, and has launched a new App Directory (don't call it a "store"!) that can be ...