Informal Safety Guarantees for Simulated Optimizers Through Extrapolation from Partial Simulations. (arXiv:2401.16426v1 [cs.LG])

Self-supervised learning is the backbone of state of the art language
modeling. It has been argued that training with predictive loss on a
self-supervised dataset causes simulators: entities that internally represent
possible configurations of real-world systems. Under this assumption, a
mathematical model for simulators is built based in the Cartesian frames model
of embedded agents, which is extended to multi-agent worlds through scaling a
two-dimensional frame to arbitrary dimensions, where literature prior chooses
to instead use operations on frames. This …

art arxiv cs.lg dataset language loss modeling predictive safety self-supervised learning simulations state state of the art supervised learning systems through training world