AI and Programming
The components of agent memory - anthropic https://mp.weixin.qq.com/s/qtnDtNjS6lYJCiPfPMCVWg
New context engineering challenges in late 2026
How JetBrains Built Cross-Database Queries into DataGrip with DuckDB
Bringing Local Analytics to the Quant’s Desktop
Long-horizon agents and durable execution
Rebuilding the global town square from scratch
Thoughtworks《技术雷达》第35期: 超越前沿大模型迷思, 让更多智能体投入生产
Making AI Agents Safe Open Agent Safety Platform
Vane 轻量级 向量 + BM25 混合检索库
Exact It runs natively on the web, macOS, iOS, and Linux, from Expo
Why Vector-Only RAG Fails on Analytical Questions, and a Reference Architecture That Doesn’t - couchbase https://github.com/couchbaselabs/CouchbasePrism
How Stanford Teaches AI-Native Engineering — Mihail Eric, Monaco
Modern Web Guidance 1.0:为您的编程智能体补齐 Web 平台专业知识
STE80 Humanizer makes AI-written text read like a careful person wrote it
The Architecture Harness: Why Software Architecture Has to Become Executable in the Agentic Era
How To Use Decision Models for Evals
How Isometric Pixel City Was Made
How we built Claude Code auto mode: a safer way to skip permissions
How to Train Your own Decision Model like Jev using Unsloth
Harness 已经很准了,为什么还需要一个 Agent Native Database
Others
The Story of How McDonald’s First Got Its Start
与一、二级投资人聊 Anthropic 招股书:泡沫、增速下滑和 coding 之后是什么