description
Palisade Research researches offensive AI capabilities to better understand and communicate the threats posed by agentic AI systems. They create concrete demonstrations of dangerous capabilities to advise policy makers and the public on AI risks. They study dangerous capabilities in automated hacking, spear phishing and deception, and scalable disinformation.
Open roles
Learn more
80,000 Hours links
Information security in high-impact areas
Career review
AI safety technical research
Career review
Preventing an AI-related catastrophe
Problem profile