Original Summary

Byte-level predictive-coding kernel that learns online from local prediction errors: no backpropagation, no attention matrix, no optimizer. Sparse fixed-fan-in synapses, slot-free distributed episodic memory, lesion-controlled reproducible experiments.

  • 情报分类：综合情报
  • 分类依据：内容未命中明确的垂直分类规则，归入综合情报
  • 信息来源：GitHub · AI 新项目
  • 发布时间：2026/9/13 18:40:57