Day 1 | Stage 1

Large language models are now capable of automating attacks previously only possible by human adversaries. Discusses several ways adversaries could misuse current models to cause harm at larger scale and lower cost than currently possible. Recent state-of-the-art models can find 0-day vulnerabilities in large software projects extensively tested by humans for decades. These new capabilities alter the threat landscape and require rethinking security.

Nicholas Carlini is Research Scientist, Anthropic.

Watch on YouTube: https://www.youtube.com/watch?v=1sd26pWhfmg