Aisle用开源小模型加搜索，在零日漏洞发现上追平了Mythos，伯克利8项里拿了3项第一，还能离线跑，挺牛的。
Mythos普及了用LLM寻找漏洞的思路，但Aisle更早开始实践。Aisle使用小规模开源权重模型配合结构化搜索系统，成功匹配了带CVE的公共零日漏洞，且可离线运行。伯克利研究在8个类别中给予Aisle全球第1的排名（3项），团队来自欧洲且规模很小。
While Mythos has popularized the idea of finding vulnerabilities with LLMs, Aisle was doing it earli...
While Mythos has popularized the idea of finding vulnerabilities with LLMs, Aisle was doing it earlier. From an engineering point of view, it's interesting to see that a small, open weight model with a structured search system is competitive at this task Stanislav Fort @stanislavfort We matched Mythos on public zero-days with CVEs using widely available & open-source derived models & can run it air-gapped if needed. All this with a small team out of Europe Berkeley study ranks us #1 globally in 3 of 8 categories The full evidence: https://t.co/NGVaWxFneq 🔗 View Quoted Tweet 💬 4 🔄 2 ❤️ 43 👀 9006 📊 9 ⚡