Continuously hardening ChatGPT Atlas against prompt injection

OpenAI is strengthening ChatGPT Atlas's defenses against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent's defenses as AI becomes more agentic.

Summary written by Kernelia from the original article by OpenAI News. The story and its rights belong to its author.