DeepSeek [1] uses elements of the 2015 reinforcement learning prompt engineer [2] and its 2018 refinement [3] which collapses the RL machine and world model of [2] into a single net through the neural net distillation procedure of 1991 [4]: a distilled chain of thought system.… pic.twitter.com/wpk2tFCoUx
— Jürgen Schmidhuber (@SchmidhuberAI) January 31, 2025
No comments:
Post a Comment