AI
GLM-5.2 & GLM-5.1 & GLM-5 https://z.ai/blog/glm-5.2
Learning on the Shop floor tobi lutke
Beyond LoRA: Can you beat the most popular fine-tuning technique?
gemma-4-webgpu-kernels Gemma 4 E2B (QAT Mobile)
CS336: Language Modeling from Scratch
你不知道的 GEO：AI 可见性的原理、实践与取舍 Tw93
Using LLMs to secure source code
Complete Agentic AI Course In 10 Hours- Langchain, Langgraph, RAG,Vectorless RAG, Guardrails,Evals
Larger Context Windows Don’t Fix RAG — So I Built a System That Does
Pydantic AI v2: capable agentic loops
I Built 11 Models to Predict the 2026 World Cup. They Crown Four Different Champions.
Migrating LiteLLM to Rust - Building the Fastest and Litest AI Gateway
拿下 OpenAI Offer 后，她复盘了 57 场面试：Transformer 要会手写，LeetCode 还得刷
Programming
HeroUI is the modern UI library for web and mobile
Sätteri A Markdown pipeline forged in Rust for the JavaScript world
砍掉 90% 冗余词元，省下 70 万美元：Netflix 开源工具狙击 AI 账单黑洞
Notes of the book System Desgin Interview - An Insider’s Guide
ValueClaw Strategy Orchestrator — managing autonomous trading strategies, monitoring market conditions, and coordinating 97 specialized skills across 17 categories through a token-efficient progressive discovery system.
Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload
Apache Iceberg Optimization: A Guide
Building a LangChain-Style AI Agent in the Browser Using Chrome’s Prompt API and Web Workers
How OpenTelemetry traces LLM Calls, Agent Reasoning, and MCP Tools
Context Specs — the full story from capitalone
Parse Scanned PDFs for RAG with EasyOCR: Free OCR Gives You Words, Not a Document