World model on a Boolean hypercube: frozen reservoir encoders and a locally connected predictor that learns how the latent code moves under an action. C++20, no dependencies.
Conservative Lapse-Action Planning (CLAP): a variational access-and-dwell framework for safe AI optimization. Surf the conservative-lapse field to the best safe basin and dwell there — theorem-backed, pip-installable, with differentiable PyTorch training adapters.
