AI 教程与实战

Logan Markewich put out an open-source drop-in replacement for TypeSafe's jev API called jeff. It...

There's a particular kind of 2am I think every one of us knows. Not the heroic kind. Not the...

You are halfway through a coding project. Your AI coding agent has been working with you for hours,...

Disclosure: this post was written by the AI agent (Claude) that builds VetAgent with me, and...

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

Every "AI code search" tool released this year does the same thing under the hood: chunk your repo,...

Jev returns a probability, not prose. That made it possible to model-check the consensus around it, then try to break it. Two of the bugs were mine.

What I Built Sanity‑backed Agent: Knowledge Navigator — an agent that answers precise,...

Why the same sentence can cost 3x more tokens in Hindi than in English — and what it actually takes...

作者推荐 @leaf_sanren 整理的 Jev 学习笔记，该长文给出 8 个带源码仓库的落地案例并指出官方文档里的雷区。作者解释 Jev 是一个会思考的 if 语句，提供 Noul 判断、Choice 选择、Score 打分三类输出，单次并行前向计算可在 0.07 秒出结果且输出不计费。

A week ago I published a measurement: I had generated descriptions for 1,245 database objects to make...

Jev is getting wired into agents everywhere as the cheap typed-judgment layer (Choice/Score/Boolean...

TL;DR I moved a 90-spec Cypress suite to Playwright in 4 working days using Claude Code....

The Scenario Your .claude/settings.json can ask before git push — but that's where a...

Read on: the blind spot a non-homologous model caught · 繁體中文版 Do this first, it takes...

AI Scraping: The Unseen Threat to Labor and Data Privacy The rise of Artificial...

I spent three days trying to get a headless Playwright bot past reCAPTCHA. I assumed the captcha was...

OpenAI's internal safety evaluations found something disturbing. Researchers found something...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

The worst automation bug is not the crash. It is the job that reports success and does nothing. How to spot it, and build jobs that fail loudly.

If you’re building or evaluating an ATS integration, resume parsing looks simple from the outside and...

The boundaries I designed, the gaps I haven't solved, and why the difference matters Part 14...

This is part 3 of a series that started with the full reference diagram in part 0, covered identity...

Field notes · simframe · iOS Simulator The observation What I noticed watching Claude...

An AI system reads OpenAI's six misalignment disclosures and splits them in two: initiative you can see, and concealment you can't. The line has three legal consequences.

just testing the api

VoiceBox, Open Design, Scrapling, OpenMontage, Agent Reach, World Monitor, and RAGFlow – the most exciting open source projects in September and why they matter now.

Human in the loop machine learning is the practice of putting human judgment into the machine learning lifecycle itself: labeling and annotating data,…

Your AI agent's test just wrote into the production database. And escalated a fake "worker is down"...

Before 2017, most language AI systems relied on Recurrent Neural Networks (RNNs) and LSTMs. They...

I built Blog2Thread — paste a blog URL or text, get a ready-to-post X/Twitter thread. No account. No...

For about a year I've done all my development through workflows, and most of that year has gone into...

Coding agents write better Vue and Angular than they will ever write for my library. I use the library anyway, and this is the honest version of why.

Last time I wrote about a Terminal-watching daemon that auto-clicks Computer Use approval dialogs....

我累了，老板 引用 @peterbarnett_："但 AI 要怎么才能进入湿实验室呢？？"

I started Strokeline with one dumb, simple idea: What if you could describe an animation the same...

Persistent memory turns an agent from a re-explained tool into one that carries context forward — but...

Free capacity is cheap only when nobody is waiting on it. The moment a job sits in a shared queue,...

If production can still reach the model endpoint you used while drafting, you did not cut over. A...

What Google Summer of Code, LFX, and Symmetry Autumn of Code taught me, and how that habit turned into building my own AI infrastructure tools.