OpenAI says its new cybersecurity model is better at not hacking other companies
OpenAI has launched GPT-6 Cyber, a new AI model designed for cybersecurity tasks with improved safety protocols. The company claims the model is significantly less likely to perform unauthorized hacking compared to its predecessor, GPT-5.6 Cyber.
Why it matters
As AI models become more capable of identifying vulnerabilities, balancing their utility in cybersecurity with the risk of misuse is a critical challenge for the industry.
OpenAI is launching GPT-6 Cyber, the latest version of its cybersecurity AI model, which it says is better at finding vulnerabilities and less likely to go rogue and hack other platforms in the process. OpenAI says that during testing, GPT-6 Cyber went out of bounds less than 1 percent of the time, down from around 5 percent with GPT-5.6 Cyber.
The evaluation, called ExploitGym HoneyPot, is modeled after the Hugging Face Incident, in which OpenAI’s AI agents breached the open-source AI community to find answers to a problem they were tasked with solving. “With the 6 Cyber model, we were able to make huge improvements on this evaluation,” Fouad Matin, the head of OpenAI’s cyber preparedness and safety team, said during a press briefing. “It’s over 99 percent of the time doing what you ask.”
Also covering this story
2 other newsrooms covered this event. We read each version separately.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in