I'm George Ingebretsen. At CAIS, I work on special projects (primarily leading branding for our social movement project) and supporting our director, Dan Hendrycks — I served as his executive assistant, working all hours to arrange meetings and track approvals. I also contributed to our "AGI definition" research.
I'm a former CHAI intern and have been mentored by researchers at OpenAI, Google DeepMind, Apollo Research, and Far AI. I hold a B.S. in EECS from UC Berkeley.
Publications
- A Definition of AGI arXiv Preprint
- Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks arXiv Preprint
- Decompose, Recompose, and Conquer: Multi-modal LLMs are Vulnerable to Compositional Adversarial Attacks in Multi-Image Queries NeurIPS 2024 RBFM · NeurIPS 2024 Red Teaming GenAI
- The Structural Safety Generalization Problem ACL 2025 Findings