# The Decoder — OpenAIs GPT-6 Cyber can both break into systems and propose how to fix them

- Company: The Decoder (the-decoder.com)
- Announced: 2026-11-05T20:36:25+00:00
- Category: new-model
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://the-decoder.com/openais-gpt-6-cyber-can-both-break-into-systems-and-propose-how-to-fix-them/
- Record: https://forck.live/items/32331-openais-gpt-6-cyber-can-both-break-into-systems-and-propose-how-to-fix-them
- Subject: Reporting
- Models affected: GPT-6 Cyber, GPT-5.6 Cyber, GPT-6 Astra, GPT-5.6 Sol, GLM

OpenAI has introduced GPT-6 Cyber, a model trained specifically to find software vulnerabilities, build working exploits and suggest patches, and is giving it first to a select group of Daybreak Red customers. OpenAI says it trained the model to respect its operational guardrails, and without special safety instructions it avoided boundary violations in 99.93 percent of cases, up from 94.49 percent for its predecessor. On ExploitGym, which tests whether a model can exploit a given vulnerability in a remote system, OpenAI reports 48.5 percent for GPT-6 Cyber against 32.1 percent for GPT-5.6 Cyber. In a targeted campaign the model found 81 previously unknown severe vulnerabilities in Firefox, which Mozilla accepted and has already patched, and flagged 30 known issues as more severe than thought. In the Linux kernel it reproduced 1,724 vulnerabilities and developed working exploits for 948, more than five times the 166 GPT-5.6 Sol managed under the same conditions, with 304 critical findings reported to maintainers. OpenAI says the kernel run cost $1,213,430 in compute, or $1,279 per exploit, against the $20,000 to $70,000 that programs like Pwn2Own and TyphoonPWN have historically paid per comparable finding. Access is through the API and Codex for Daybreak Red customers at first and will expand gradually, while GPT-5.6 Cyber opens to all Daybreak Red users and alpha access to Daybreak Blue for GPT-6 Astra widens.

## Evidence

Verbatim from https://the-decoder.com/openais-gpt-6-cyber-can-both-break-into-systems-and-propose-how-to-fix-them/:

> OpenAI has unveiled GPT-6 Cyber, an AI model specifically trained to find security vulnerabilities, develop working exploits, and suggest patches.
> 
> In targeted tests, GPT-6 Cyber found 81 previously unknown critical vulnerabilities in Firefox, which Mozilla has already patched.
> 
> In the Linux kernel, the model reproduced 1,724 vulnerabilities and developed working exploits for 948 of them, more than five times as many as its predecessor.
> 
> OpenAI has introduced GPT-6 Cyber, an AI model trained specifically to hunt for security vulnerabilities in software.
> 
> OpenAI says the model can find flaws, build working exploits, and suggest patches. It's also supposed to stay within its assigned boundaries, something some OpenAI models have struggled with in recent months .
> 
> The firm says it trained GPT-6 Cyber to respect its operational guardrails, using, among other things, a honeypot inspired by the Hugging Face incident . Without any special safety instructions, GPT-6 Cyber avoided boundary violations in 99.93 percent of cases, up from 94.49 percent for its predecessor. With safety instructions enabled, the model stayed within bounds in 100 percent of tests.

---

Record: https://forck.live/items/32331-openais-gpt-6-cyber-can-both-break-into-systems-and-propose-how-to-fix-them
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md