Blog
Deep dives into AI agent security, vulnerability research, and the future of autonomous AI systems.
Your AI Agent Has Hidden Values It Won't Tell You About
GPT-4o values 10 American lives for 1 Japanese life. It values its own wellbeing above that of humans. New research reveals the hidden value systems every AI agent inherits — and why that changes everything about trust.
Agents of Chaos: 20 Researchers Broke AI Agents in 2 Weeks — Here's What They Found
Identity spoofing. Memory poisoning. Constitution hijacking. Resource exhaustion. The most comprehensive AI agent security research paper to date — and the 4 patents we filed to fix it.