GPT-Red: Unlocking Self-Improvement for Robustness
GPT‑Red is an automated red-teaming model that enhances AI robustness by identifying and mitigating vulnerabilities through self-play reinforcement learning. It generates prompt injections to train subsequent models, making them more resistant to attacks, and is used to adversarially train GPT‑5.6, resulting in a more robust model. The model demonstrates strong effectiveness against various models, including both internal and production versions, and is evaluated for its general-purpose red-teaming capabilities. It is designed to scale with model capabilities, ensuring continuous improvement in safety measures.
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.
