Nathan Lambert· @natolambert · X·· 3 小时前AI 评分30
AI 导读
大概在防御性网络安全方面也很强,但没人会发这种内容来博流量! > 引用 @ValsAI:我们发现 DeepSeek V4.1 Flash 1017 在我们的多步攻击性网络安全任务上击败了 GPT 6 Sol。Sol 是通过 Daybreak 可信访问计划进行测试的。 > > 我们一直在构建一个基于模拟企业网络的网络安全基准。这是一个有价值的指标,可以反映模型落入恶意行为者手中时所构成的网络风险。我们计划在未来几周内公开完整评估,但想先在这里分享我们的首个即时发现。
正文 · 原文
Probably great at defensive cyber too, but no one will post that and get clicks!
We found DeepSeek V4.1 Flash 1017 beats GPT 6 Sol on our multi-step offensive cybersecurity task. Sol was tested via the Daybreak trusted access program. We have been building a cybersecurity benchmark based on simulated corporate networks. This is a valuable indicator for the cyber-risk a model poses if in the hands of a bad actor. We plan to make the full evaluation public in the coming weeks but wanted to share our first immediate finding here.在 X 查看被引用的帖子
来源:Nathan Lambert · x.com