tech
OpenAI trained an AI for red-teaming AI.
The new GPT-Red model “can break nearly all models it is pitted against,” according to an OpenAI blog post on Wednesday. OpenAI says it used GPT-Red to find vulnerabilities in GPT-5.6 Sol, a process that made it the company’s “most robust model to prompt injections to date.”
TL;DR
- OpenAI created a new AI model called GPT-Red.
- GPT-Red is designed to find vulnerabilities in other AI models.
- The model was used to identify weaknesses in GPT-5.6 Sol.
- GPT-Red is described as the company's most robust model to date against prompt injections.