Nicholas Carlini - Black-hat LLMs | [un]prompted 2026

Name: Nicholas Carlini - Black-hat LLMs | [un]prompted 2026
Description: Nicholas Carlini of Anthropic talks at [un]prompted 2026 about how adversaries could misuse current LLMs for attacks. He shows recent models finding zero-day vulnerabilities in heavily tested software, including a SQL injection in Ghost.

unprompted

Nicholas Carlini of Anthropic talks at [un]prompted 2026 about how adversaries could misuse current LLMs for attacks. He shows recent models finding zero-day vulnerabilities in heavily tested software, including a SQL injection in Ghost.

HN cites it as a concrete demonstration that LLMs have suddenly become strong at finding and exploiting vulnerabilities.

16 Hacker News mentions · 2026–2026

Topics

Security & hacking
LLMs & generative AI

Watch on YouTube

Explore more videos