AI Intelligence Archive

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....

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.

A backend engineer opened a pull request at sixteen forty after an afternoon spent steering a coding...

I’ve been experimenting with AI integration in software applications for some time, not as an...

You type a sentence into ChatGPT and it looks like normal English. The model doesn't see it that...

My last two posts gave rates with a self-selected denominator. This one fixes that: a generation-sliced sample of active repos (6.2%) and a uniform sample of the whole repo population (1.0%), plus the ecosystem numbers that surprised me.

I got the rejection email on a Tuesday. I've been rejected before — everyone has. This one broke...

Model Context Protocol with Spring AI: Building MCP Clients and Servers in Java In the...

What I Built Cthulhu’s Inbox is an interactive, retro-horror workplace simulator where the...

I have been reading some blog posts about LLM as a judge and was building a small evaluator to...

Be honest: what do you actually do while the agent types? I used to just watch. Not read, watch....

I built a Magic 8 Ball on Jev, TypeSafe's calibrated-decision model, and misread its three primitives four times. The measured numbers, and what each mistake cost.

You ask the agent about the payments retry table, and it comes back with the retry table plus the...

When the llms.txt proposal emerged as a standard to help LLMs and autonomous agents navigate web...

Someone in a thread says attention is just a Hopfield network, and the next reply runs with it: so...