This post is crossposted from my Substack, Structure and Guarantees, where I explore how formal verification might scale to more complex intelligent systems. The starting point here is the familiar idea of predictive coding, where a learning loop refines a model of the world based on prediction errors. The twist...
This post is crossposted from my Substack, Structure and Guarantees, where I’ve been exploring how formal verification might scale to more-complex intelligent systems. This piece argues that compilers—already used in limited forms of recursive self-improvement—offer a concrete setting for studying some AI-safety challenges. The previous post in this sequence is...
This article is crossposted from Structure and Guarantees, my series on full-stack design of intelligent systems with strong mathematical guarantees. This post argues that formal verification can serve as a radically accelerated fitness function for evolutionary search: dramatically faster feedback while still providing strong guarantees. The last three posts set...