Q*? 2015: reinforcement learning prompt engineer in Sec. 5.3 of “Learning to Think...” arxiv.org/abs/1511.09249. A controller neural network C learns to send prompt sequences into a world model M (e.g., a foundation model) trained on, say, videos of actors. C also learns to interpret answers of M, extracting algorithmic information from M. Acid test: does C learn its control tasks faster with M than without? Is it cheaper to learn C’s tasks from scratch, or to address algorithmic info in M in some computable way, enabling things such as abstract hierarchical planning and reasoning?  2018: collapsing C and M into a single network arxiv.org/abs/1802.08864 using the neural network distillation of 1991 xitter.cf/SchmidhuberAI/st… 1990: online planning & reinforcement learning with recurrent world models and artificial curiosity / GANs: people.idsia.ch/~juergen/wor…