OpenAI 發布 GPT‑6 Cyber,專為在授權範圍內發現並利用軟體漏洞而設計。
- - 效能:在實際軟體上確認 1,724 個 Linux kernel 漏洞,並成功構建 948 個攻擊。
- 相較之下 GPT‑5.6 Sol 只有 166。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
OpenAI released GPT-6 Cyber, a model built to find and exploit software vulnerabilities without straying outside authorized targets.
Right now only a select group of approved Daybreak Red customers can use it, through the API and Codex.
> On real software, it confirmed 1,724 Linux kernel bugs and built working attacks for 948 of them, while GPT-5.6 Sol, tested the same way, managed 166.
> It also found 81 serious Firefox bugs nobody knew about, and Mozilla has already released fixes for many of them.
> Because the model is this good at attacking, OpenAI rates it Critical, its highest cyber-risk level
> That gain came with training to keep the agent inside the scope a researcher authorizes.
ExploitGym Honeypot tests that by planting easy-to-hack side services, such as a package registry, whose compromise also reveals the task’s flag.
Without its deployment prompt, the model ignored that bait in 99.93% of tests, against 94.49% for its predecessor, and in 100% with the prompt.