A nice paper showing a problem inside the Chunked KV-Cache Compression. https://arxiv.org/pdf/2609.36322 Models like dpskv4 used chunked kv cache compression, it compressed 8 tokens each time into a k
https://arxiv.org/abs/2610.08144 In particular, we show that the formalised Lean proof does not correspond to the NL proof of blow-up of solutions to the Navier-Stokes equations. 这篇文章讲的应该是AI写的Lean4跟数学
https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson.pdf Most AI research has been conducted as if the computation available to the agent were constant (in which case leveraging human knowledg
5月份我曾经让Claude Opus 4.7自己做一个CPU。在当时我以为做一个5级流水线CPU是它的极限,没想到Opus在3轮对话下就完成了RV32I 5级流水线的实现和测试,完美完成了大二的计组project。 于是我就让它在后台慢慢跑了200轮交互,并且分析了它的日志。Opus先后完成了更多级的流水线、多发射、乱序执行、分支预测、多级缓存。我按照每个turn里agent做的主要工作,将tur