AI
OpenAI Privacy Filter OpenAI Privacy Filter is a bidirectional token-classification model for personally identifiable information (PII) detection and masking in text. It is intended for high-throughput data sanitization workflows where teams need a model that they can run on-premises that is fast, context-aware, and tunable.
Single vs Multi-Head Attention - byhand
The Prompt Engineering Cheat Sheet: How to Write Better AI Prompts - eweek
How to Build Your Own Language-Specific LLM [Full Handbook]
Dive into Claude Code: The Design Space of Today’s and Future AI Agent Systems - chapterpal https://www.chapterpal.com/
Translation Quality Benchmark - TranslateBooksWithLLMs
How to Use Transformers.js in a Chrome Extension - huggingface
Programming
pi-for-excel Experimental Excel sidebar agent add-in. Multi-model. Powered by Pi.
I Read Hermes Agent’s Memory System, and It Fixes What OpenClaw Got Wrong
ladybugdb - The embedded columnar graph database built for highly regulated industries
你不知道的 Agent：原理、架构与工程实践 from TW93
Wisely Chen｜AI Agent、地端 LLM 與企業 AI 架構實戰筆記
Others
丰饶之后：AI Coding 观察报告 2.0｜AI 透镜系列研究