← 返回归档

帖子详情

查看 X 原文
G
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 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 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：timed out
帖子 ID
2111200699128353136
Markdown
/app/data/archive/2026/10/16/goodfellow_ian/2111200699128353136/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111200699128353136"
author: "goodfellow_ian"
published_at: "2026-10-16T21:00:45+00:00"
source_url: "https://x.com/goodfellow_ian/status/2111200699128353136"
---

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](https://pbs.twimg.com/profile_images/1986657231106985984/CG2a0tus_normal.png)

Stanislav Fort@stanislavfort

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

![Tweet Image](https://pbs.twimg.com/media/HUmRkNgX0AA55Up.jpg)

[🔗 View Quoted Tweet](https://x.com/stanislavfort/status/2110386359777046951)