AI 教程与实战

Last week I open-sourced Foremerge, a coordination protocol for coding agents that sits above Git....

ZHO 分享其去年用 Gemini 3 Pro 开发的自动建模+渲染+动画流程，组合 Gemini 3 Pro 建模、Nano Banana Pro 渲染、Veo 3.1 动画，耗时由 1 小时缩短为 2 分钟。他提出核心验证是 AI 跨模态能力让渲染和动画不再依赖精确建模，效果与精确落地可分开。

A pull request can pass the compiler, the formatter, and the linter and still leave behind a serious...

I ship Codenames AI, a web game. Each game mode keeps its own save in localStorage. Reload the tab,...

Most teams running on Google Cloud don't pick one compute model and stay there. Some services live...

会议录音的目的已从给人听转为喂给 Agent，AI 摘要没人读，完整逐字稿才能保留分歧、犹豫和权衡等底层信息。作者分享三套协作协议：用唤醒词把会上判断变成 Agent 自动执行的命令流、对带时间戳的逐字稿做多角色切片、把口述会议稿直接塞给 Codex 当原型 PRD 改代码。

Previously: 9 Bugs That All Looked Like a Working System · I Built an AI That Rewrites Its Own...

Three seasons, thirty-six parts, one clinic app — and a meter that ran the whole time. Every part of...

Local inference that actually runs. Your smart camera is not smart. It's a snitch with a monthly...

GPT-6 Astra is the first model OpenAI rates 'Critical' for cyber capability. What that label means, and the tool-permission gate your agent needs anyway.

tldr Subagents architecture made of parallel read-only child agents with simple text...

I use AI coding agents a lot. And for a while, one of the most annoying parts had nothing to do with...

Ethan Mollick 让 GPT-6 阅读他数万封邮件、 writings 和日程，自主下载软件、制定策略，在五天不间断工作中无需干预地构建了数 GB 的个人 wiki，涵盖研究、联系人、想法和任务。现在该 AI 每天两次交叉核对新邮件并发送摘要简报。他提醒授权访问自己电脑存在风险需谨慎，试用期内 token 未收费，因此无法告知完整成本但可能相当可观，日常简报 token 消耗不大。

A tutorial for gh stack, and for the fact that it does not care whether the diff gets read by my lead or by an AI. Small diffs get reviewed better either way.

Databricks 发布博客，介绍组织在迈向 AI 与数据驱动时，如何借助 Databricks 构建高质量且可信的数据产品。正文从企业在 AI 和数据驱动转型中需要交付数据产品这一需求展开。

Cohere 发推称其 AI 采用 on-prem（本地部署）方式，因此如果 AI 宕机，责任在用户自己。

The current generation of AI coding agents makes it surprisingly easy to create a "skill." Write a...

Your AI stack works fine with one model. The moment you add a second provider, a fallback, a rate...

Table of Contents Why Run an AI Model at Home? What Is a Local LLM? What Kind of Computer...

Refereeing the memory-safety retrofit argument from someone who ships framework code in both Rust and Go, and likes them for different reasons.

GPT4All is an open-source graphical desktop application for running large language models (LLMs)...

Every review checklist ever written was built for a diff whose author could explain it. Here are the twelve questions that replace that assumption, why the generated tests don't count as a second opinion, and four merge gates that are actu…

A friend of mine doesn't speak English. I do most of my podcast listening in English. Every so often...

In 2001, in the final year of my Computer Science degree, I chose A_I and Neural Networks_ as an...

People have started telling me that my writing sounds like AI. I published that sentence in a...

About a year ago, I wrote a piece called Software Becomes Disposable, arguing that AI was...

Sealing the host made the naive mutation impossible and the agent useless. The fix is a Bench: a disposable environment that starts with no files and no network, where every capability is granted narrowly, per task, and revocably.

NVIDIA 发布教程，讲解在 Jetson 上部署新一代开放推理模型的方法，以 Nemotron 3.5 Lightning 和 Qwen3.8-27B 为例。

GitHub Copilot app 支持并行运行多个智能体会话，每个会话独立运行并保留各自上下文，可随时切换而不需重新说明任务。每个会话可运行在自己的 Git worktree 上实现隔离，作者以 tailspin-toys 仓库为例演示同时进行添加 funded sort 功能、无障碍审查和运行测试三个任务，用户在 sessions 视图中跟踪进度并审阅结果。

Shir Meir Lador 在 Google AI 开发者博客介绍如何用 Cloud Run instances 以每月 $5.70（1 vCPU、1Gi 内存、共享 CPU）在云端 24/7 运行常驻 Agent。

Welcome back to our series on building the ultimate AI research assistant for our AI agent podcast!...

The world of AI agents is moving at lightning speed. Keeping up with the latest trends, new...

Since May I've been building Agent Console, a small desktop app for supervising coding agents —...

A senior software engineer who knew nothing about hardware, a BACnet MS/TP thermostat, and an RS-485 bus. How I ended up with an ESP32-S3 gateway on a DIN rail, wired into Home Assistant, in 15 evenings.

Most people wire up an AI agent and then discover what it can do. I did it the other way round:...

Something broke in your app last night. A checkout flow failed, an LLM call timed out, a vector...

The following scene is a composite on-call pattern, not a personal claim about one employer. A...

My working day spans about ten Git repositories. Here is where their state actually lived: which...

What Broke In the weeks leading up to our most recent production run, our local LLM agent...

Running a local LLM is easy. Running multiple specialized models for coding, reasoning and AI agents...