AI模型最低4.24美元发现零日漏洞
AI 总结
据ZDNET报道,Xint.io测试的七个AI模型中有三个发现了私下披露的Google V8零日漏洞CVE-2026-102321。GPT 6 Sol用时13分钟、花费4.24美元,GPT 5.6 Sol用时44分钟、花费22美元;Claude Opus 5首次尝试即成功,报告成本为43.40美元。DeepSeek和Z.ai的模型未能完成,而此前模型在扫描25小时并花费350美元后仍未发现该漏洞。
深度见解
Xint.io的结果显示,配合针对性指引使用前沿模型进行漏洞研究正变得更快速、更便宜,同时也表明能否成功取决于模型及提示方式。

ZDNET’s key takeaways
- As AI advances, so does its ability to find zero-day vulnerabilities.
- Only three of seven AI models found a privately reported Google V8 bug.
- Finding a zero-day now costs as little as $4. Can defenders keep up?
Trending Now
I tried Claude Sheets on 3 tasks – and it saved me hours of work in 10 minutes 11/15/2026
#Xint.io#GPT 6 Sol#GPT 5.6 Sol#Claude Opus 5#Google V8#CVE-2026-102321#OpenAI#Anthropic#DeepSeek#Z.ai#Google Vulnerability Reward Program