Ian Goodfellow(@goodfellow_ian)
In Aisle's first year, they've shown that the system built around an LLM is highly important, and ev...
6.4内容质量
TL;DR · AI 摘要
Ian Goodfellow on X: "In Aisle's first year, they've shown that the system built around an LLM is highly important, and...
核心要点
- 主题聚焦：In Aisle's first year, they've shown that the sy
- 来源：Ian Goodfellow(@goodfellow_ian)，建议结合原文判断细节。
- AI 分析暂不可用，本条为保底评分与摘要。
#AI#编程#安全
打开原文Ian Goodfellow on X: "In Aisle's first year, they've shown that the system built around an LLM is highly important, and even small, cheap fast models can be boosted to do valuable security work" / X
Ian Goodfellow
@goodfellow_ian
In Aisle's first year, they've shown that the system built around an LLM is highly important, and even small, cheap fast models can be boosted to do valuable security work
Stanislav Fort
@stanislavfort
Oct 14
My AI security research lab AISLE discovered 500+ zero-days with CVEs across 100+ codebases in a year => ~1% of 2026's open-source CVEs globally from a single team! On hardened codebases like curl, we've repeatedly matched or outperformed frontier AI labs in zero-day discovery
9:00 PM · Oct 16, 2026
·
8,840
Views
5
63
18