Hermes Agent already remembers across sessions. The open-source agent from Nous Research ships with curated memory files and full-text session search. But a new community project argues that built-in memory is too shallow for serious work. A new library named…

MiniMax officially released MiniMax M3 on June 1, 2026. The model introduces MSA (MiniMax Sparse Attention), a new sparse attention architecture that gives M3 a 1M-token context window. M3 also supports image and video input and desktop computer operation…

The Transformer’s attention mechanism has barely changed since 2017. Most efficiency work has tried to replace softmax attention outright. A new paper takes a different route. It keeps softmax attention and bolts on a correction branch. A team of researchers…

过去两年AI基础设施的叙事几乎都围绕GPU、HBM和液冷。但真正走进机房会发现，GPU不是孤岛。一个大模型训练集群的本质不是"一堆卡"，而是一台由几十万颗加速器、交换芯片、网卡、铜缆、光纤和光模块拼出来的分布式计算机。 这台计算机最怕的不是某一张卡算不动，而是卡和卡之间说话太慢。 所以光模块这条线突然从通信行业的角落，变成AI capex里的关键瓶颈。TrendForce在2026年4月的判断很直接：AI光模块市场预计从2025年的165亿美元增长到2026年的260亿美元，同比增长超过57%；同时，EML（Electro…