探索技术前沿，连接数字世界

DeepSeek-V3.1-GGUF 1-bit～16-bit 对比和选择

核心定义与背景 DeepSeek-V3.1 基础模型 总参数…

AI大模型量化方法及下载地址

1. 什么是模型量化 模型量化是将高精度的模型（通常为 32…

银河麒麟(KylinOS)下DeepSeek的四种使用场景

如何在银河麒麟使用DeepSeek？ 最近国内AI大模型De…

安装银河麒麟桌面系统V10【超详细图文教程】

1、下载安装镜像 1.1 申请试用 银河麒麟官网提供免费试用…

GitHub 镜像站点

国内访问 GitHub 有时会遇到速度慢或不稳定的情况，这时…

2024年国内外AI领域开源常用大模型资料汇集及资源下载部署方法（持续更新中）

一、介绍 目前，开源大小模型较多，在实际应用过程中遇到调试和…

2028年10大战略预测数据分析

面向未来的数据分析建议 战略规划假设能够帮助您识别、理解和规…

Fragments: July 13

Some more of my notes from Tho…

DSLs Enable Reliable Use of LLMs

LLMs generate code incredibly …

The Archaeologist’s Copilot

I built 31 developer tools in a weekend — here’s what I learned

Every time I want to format a …

Where Code Meets Medicine, Chemistry, and Even Religion

GitHub: Where Code Meets Medic…

You Deleted It. The Crawler Still Sees It.

I removed two listings from a …

One line of math froze my AI agent forever. The timeout watched and did nothing.

This is my second entry for th…

What happens after a write? Reworking Squirix’s WAL in preview.6

In my first Squirix article, I…

Constrained Decoding vs Post-hoc Validation: Production LLM Extraction Needs Both

Constrained decoding and post-…

Your n8n Workflow Passed Schema Validation—and Updated the Wrong Customer

A workflow can finish successf…

PyGo: A Deep Learning Framework Where Go Calls Python Calls C++

[Project] PyGo – embedding CPy…

How Netflix Doesn’t Crash During Peak Hours (Cloud Concepts) ! 😱

Millions of people open Netfli…