Lend the shell of Claude Code to other models, and keep the configurations of MCP
Lend the shell of Claude Code to other models, and keep the configurations of MCP, skills, and CLAUDE.md as they are. It also comes with a real session scoring tool to tell you whether the model can withstand it. Lupine is a small agent that runs locally. The shell of Claude Code remains unchanged, and the inside is replaced by another model. MCP…
In actual testing, GLM-5.3 outperformed DeepSeek V4 Pro. This generation of GLM model has very unique capabilities and is really worth using.
It feels like every model factory is beginning to find its own unique path.
DeepSeek-SSD is on GitHub
An SSD streaming engine to run DeepSeek V4 Flash on Windows
Is DeepSeek V4 Pro overturned? Many people started to curse.
But when I read DeepSeek’s technical report today, I found out why the video memory didn’t explode when 1 million tokens were inserted into the context. This report has a total of 58 pages, and I only focused on two numbers: the amount of single-token inference calculations and the KV cache. When V4 Pro has 1 million tokens, the calculation amount of single token inference is about 27% of that of V3, KV…
You have reached the end of the archive
All of deepseek