Alignment Arithmetic Reinforcement Learning and Certifiable Game Plans Can we certify the plan of a powerful but possibly adversarial AI? Interpretability Expanding Merlin-Arthur Classifiers Can we stabilise the Merlin-Arthur setup for complex dataset/text data? Robustness Mixed Integer Linear Programs for Adversarial Robustness Make certified robustness bounds for neural networks feasible via a new algorithm based on MILP solvers.