OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...

Red, an AI-powered red-teaming model that finds vulnerabilities before deployment, making GPT-5.6 its most secure and ...

OpenAI has doubled its biosecurity bounty to $50,000, inviting vetted researchers to test whether GPT-5.6's biosafety ...

Forget the XML blocks and persistence scripts. OpenAI’s new prompt guide says define the destination, set conditions, and get ...

It's refreshing when a leading AI company states the obvious. In a detailed post on hardening ChatGPT Atlas against prompt injection, OpenAI acknowledged what security practitioners have known for ...

Red, an internal artificial intelligence system it built to attack its own models and surface prompt injection ...

OpenAI announced a new feature that it says will provide additional protection from prompt injection attacks, where malicious chatbot instructions are hidden in web pages and other content sources.

In a dual move to secure its technological and social license, Sam Altman-led OpenAI has formalized a research alliance with the U.S. Department of Energy (DOE) and overhauled safety protocols for ...

Cybercriminals don't always need malware or exploits to break into systems anymore. Sometimes, they just need the right words in the right place. OpenAI is now openly acknowledging that reality. The ...