Matthias Ott“LLMs can autonomously, and without fancy scaffolding, find and exploit 0-day vulnerabilities in critical software. This is not something that was true even, let’s say, three or four months ago.”
Nicholas Carlini - Black-hat LLMs | [un]prompted 2026
Nicholas Carlini, Research Scientist, Anthropic, speaks at [un]prompted 2026 on: Black-hat LLMs.Large language models are now capable of automating attacks t...