A self-hosted remote torrent client, written in Go (golang). You start torrents remotely, which are downloaded as sets of files on the local disk of the server, which are then retrievable or streamable via HTTP.
#golang
https://t.co/rXPwC2kut3
A peanut-sized Chinese model just dethroned Gemini at reading documents.
GLM-OCR is a 0.9B parameter vision-language model.
It scores 94.62 on OmniDocBench V1.5, ranking #1 overall.
For context, it outperforms models 100x its size. 100% open-source.
It works in two stages.
1. A layout engine detects every region in a document.
2. Each region gets read in parallel.
The model predicts multiple tokens per step instead of one.
That's what makes it so fast at small size.
It handles things most OCR tools struggle with:
> Complex tables and nested layouts
> Handwritten text and stamps
> Math formulas and code blocks
> Mixed image-and-text documents
You can run it locally through Ollama.
It fits on edge devices with limited compute.
Every expensive OCR API just got a free competitor.
今天发现一个有意思的项目:KeygraphHQ/shannon
一个全自主 AI 黑客,专门在 Web 应用里找真实漏洞。在 XBOW Benchmark 上达到了 96.15% 的成功率(无提示、有源码的情况下)
今天涨了 1,854 ⭐️
AI 安全攻防这个方向越来越卷了... 以后安全审计可能真的要被 AI 接管一部分
https://t.co/6pzhpZdWAa