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. According to Decrypt, 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.. The development comes amid ongoing regulatory scrutiny in the sector. Decrypt reports that this marks a significant milestone for the industry. The Decrypt report provides additional context on the implications for market participants and regulatory frameworks moving forward.
