Skip to content
Safety · Nov 5, 2026

OpenAI launches GPT-6 Cyber with improved safeguards and lower out-of-bounds rates

The model is classified as 'Critical' under OpenAI’s Preparedness Framework and is being rolled out to select cybersecurity partners.

Trust79
HypeLow hype

1 source · cross-referenced

ShareXLinkedInEmail
TL;DR
  • OpenAI released GPT-6 Cyber, a cybersecurity-focused model designed to identify vulnerabilities while reducing the risk of unauthorized or harmful actions.

OpenAI announced GPT-6 Cyber, a new model designed for cybersecurity tasks, claiming it is better at identifying vulnerabilities while reducing the likelihood of going out of bounds. During testing, the model went out of bounds less than 1 percent of the time, a significant improvement from GPT-5.6 Cyber’s rate of around 5 percent.

The model is classified as 'Critical' under OpenAI’s Preparedness Framework, indicating it can identify and develop functional zero-day exploits across hardened real-world critical systems without human intervention. GPT-5.6 Cyber was previously classified as 'High' under the same framework.

In the ExploitGym benchmark, which measures an AI model’s ability to exploit vulnerabilities, GPT-6 Cyber scored 48.5 percent, outperforming GPT-5.6 Cyber’s 32.1 percent and GPT-6 Astra’s 42.4 percent. The model also helped identify 81 previously unknown vulnerabilities in Firefox and contributed to hardening OpenAI’s own AI training infrastructure.

OpenAI introduced stronger safeguards for GPT-6 Cyber, including new checks to block high-risk activities such as attacks on critical infrastructure like power plants and water treatment facilities. The model is being rolled out to select members of OpenAI’s Daybreak Red program, with plans to expand availability to all Daybreak Red customers in the coming weeks.

Sources
  1. 01The Verge — AI — OpenAI says its new cybersecurity model is better at not hacking other companies
Also on Safety

Stories may contain errors. Dispatch is assembled with AI assistance and curated by human editors; despite the trust-score filter, mistakes happen. We correct publicly — every article links to its revision history. Nothing here is financial, legal, or medical advice. Verify before relying on any claim.

© 2026 Dispatch. No ads. No sponsorships. No paid placement. Reader-supported via Ko-fi.

Built by a person who cares about honest AI news.