OpenAI says its new cybersecurity model is better at not hacking other companies

<figure> <img alt="Vector illustration of the Open AI logo." data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2025/02/STK155_OPEN_AI_2025_CVirgiia_D.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">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.</p> <p class="wp-block-paragraph">The evaluation, called ExploitGym HoneyPot, is modeled after the Hugging Face Incident, in which <a href="https://www.theverge.com/ai-artificial-intelligence/968988/openai-hugging-face-hack-ai">OpenAI's AI agents breached the open-source AI community</a> 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," Fo …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/1027599/openai-gpt-6-cyber-launch">Read the full story at The Verge.</a></p>