📰 OpenAI Launches GPT-6 Cyber: ExploitGym 48.5%, Out-of-Scope Rate Down to 0.07%, Daybreak Red Select Access, Critical Preparedness
On November 5 OpenAI launched GPT-6 Cyber for authorized security research: ExploitGym rose from GPT-5.6 Cyber's 32.1% to 48.5% (about 51% relative), out-of-scope exploitation fell to 0.07% without deployment prompts and 0% with them.
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 OpenAI 发布 GPT-6 Cyber:ExploitGym 48.5%、越界率降至 0.07%,Daybreak Red 精选客户可用,预备度升至 Critical
OpenAI 于 11 月 5 日正式推出面向授权安全研究的 GPT-6 Cyber:ExploitGym 从 GPT-5.6 Cyber 的 32.1% 升至 48.5%(相对提升约 51%),无部署提示时越界利用率仅 0.07%、有提示时为 0%。
💬 你怎么看?欢迎在评论区讨论。
#OpenAI #GPT-6 Cyber #Daybreak Red
0 Comments
