MAI-Cyber-1-Flash模型搭配MDASH在CyberGym基准达96%,成本减半

Big news! Our new MAI-Cyber-1-Flash model combined with MDASH, our multi agent security harness, del...

精选理由

快看,MAI-Cyber-1-Flash在安全基准上拿96%,比Mythos高12个点还便宜一半,性价比炸裂!

AI 摘要

Mustafa Suleyman宣布MAI-Cyber-1-Flash模型与MDASH多智能体安全框架结合,在CyberGym基准测试中得分96%。该成绩比Mythos模型高出12个百分点。推理成本仅为Mythos的一半。更多细节将在后续帖子中披露。

原文 · Mustafa Suleyman

Big news! Our new MAI-Cyber-1-Flash model combined with MDASH, our multi agent security harness, del...

Big news! Our new MAI-Cyber-1-Flash model combined with MDASH, our multi agent security harness, delivers 96% on the CyberGym benchmark, 12pts above Mythos, at HALF the cost. Proud of the team. More details in THREAD: 💬 14 🔄 19 ❤️ 142 👀 21148 📊 30 ⚡

MAI-Cyber-1-Flash模型搭配MDASH在CyberGym基准达96%,成本减半 · AI 热点