AI
Chasing 100% Accuracy: A Deep Dive into Debugging Kimi K2’s Tool-Calling on vLLM
愛好 AI Engineer 電子報 🚀 2025 Q4 AI 模型與 Agent 開發 #33
The 2025 Hype Cycle for GenAI Highlights Critical Innovations- gartner
Towards Scalable Pre-training of Visual Tokenizers for Generation
An Empirical Study of Agent Developer Practices in AI Agent Frameworks
MiniMax海螺首次开源，发现了AI视觉生成领域的Scaling Law
Part 1: Tokenization, Building an LLM From Scratch in Rust
RAG回答不全？上下文扩展+二次重排让召回率从42%提升到89%
Scaling LLMs to larger codebases
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
The 2025 AI Engineer Reading List
Programming
Prompt caching: 10x cheaper LLM tokens, but how?
jax-js: an ML library for the web
How to Build an AI Agent with LangChain and LangGraph: Build an Autonomous Starbucks Agent
pdfplumber Plumb a PDF for detailed information about each text character, rectangle, and line. Plus: Table extraction and visual debugging.
Performance Hints from Jeff Dean, Sanjay Ghemawat
mgrep semantically grep everything, like code, images, pdfs and more.
ScholArxiv allows users to search, read, bookmark, share, download and view summaries of academic papers from the arXiv repository
The Garbage Collection Handbook
Gemini Lossless Watermark Remover - banana.ovo.re
scribbler JavaScript Compiler and Notebook Tool
Infographic AntV Infographic is AntV’s next-generation declarative infographic visualization engine
Web Development in 2025: AI’s React Bias vs. Native Web
DocSummarizer Part 3 - Advanced Concepts: The “I Went Too Far 🤦” Deep Dive
Where Architects Sit in the Era of AI
Others
The Strange Case of Engineers Who Dismiss AI
My AI Colleague: Claude, the good, the bad, the UglAI