Geoffrey Irving, former Chief Scientist at the UK AI Safety Institute, argues that current lab safety paradigms will fail when AI reaches superintelligence, calling for mathematical rigor, public proof of obstacles, and foundational alignment theory. He contends that slowing down AI development is already overdue due to the divergence between capability improvement and alignment verification.
Former UK AISI Chief Scientist Geoffrey Irving dissects why current lab safety paradigms will fail when AI crosses the threshold into superintelligence. Analyzing the divergence between AI capability hill-climbing and alignment verification, Irving argues that slowing down is already past due, requiring mathematical rigor, public proof of obstacles, and foundational alignment theory.
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.