Selected Publications

Whitepaper: “A neurosymbolic world model for fundamental investing at scale”. Coming soon.

Publication: “Free Energy Risk Metrics for Systemically Safe AI: Gatekeeping Multi-Agent Study”. Download from arXiv.org. Feb/2025

Preprint: “Collaborative risk management from first principles: an urban mobility case study”. To be presented at the Active Inference Symposium. Nov/2024

Presentation: “Gaia: Distributed planetary-scale AI safety”. Presented at the Guaranteed Safe AI Seminar. Jun/2024