rich-sutton

Rich Sutton 讨论了在人工智能研究中依赖一步预测的常见错误，并提倡使用选项和GVF的时间抽象模型。

Rich Sutton argues that generative AI trained by supervised learning cannot achieve genuine novelty and quality simultaneously, and that true discovery requires a 'vary, evaluate, select' mechanism found in reinforcement learning rather than pure imitation.