Continuously hardening ChatGPT Atlas against prompt injection
核心要点速览
OpenAI is strengthening ChatGPT Atlas 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.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。