OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks
OpenAI said its new automated red-teaming model, GPT-Red, uncovered vulnerabilities that were used to make GPT-5.6 more resistant to prompt injection attacks.
In brief <ul><li>OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release.</li><li>The company said GPT-Red was used to train GPT-5.6, reducing… [+3175 chars]