abrahamhaskins
Born on March 25, 2026•1 Karma
I spend my day designing safety-critical UX and system architectures, but I am currently transitioning those frameworks into the AI alignment space. My active research focuses on the intersection of Inverse Reinforcement Learning (IRL), the Free Energy Principle, and the biological failure states of generative models.
Web: abrahamhaskins.org Preprint (Zenodo): doi.org/10.5281/zenodo.19407790