news
Sean Heelan's Blog
January 18th, 2026 at 8:51 PM

On the Coming Industrialisation of Exploit Generation with LLMs

Recently I ran an experiment where I built agents on top of Opus 4.5 and GPT-5.2 and then challenged them to write exploits for a zeroday vulnerability in the QuickJS Javascript interpreter. I added a variety of modern exploit mitigations, various constraints (like assuming an unknown heap starting state, or forbidding hardcoded offsets in the […]

#ai
#llm

Get stories like this every Monday

The week's most important AI news in one email. Free, unsubscribe anytime.

Score: 2.00

Engagement proxy: 0

Canonical link: https://sean.heelan.io/2026/01/18/on-the-coming-industrialisation-of-exploit-generation-with-llms/