AI Intelligence Archive

The Problem, In One Sentence Data catalogs are excellent at telling you your data is...

A year ago, I was the senior engineer on the team. Today, a junior with Copilot can match my output...

Martin McGarry's top tip: query the bare OpenAI or Gemini API, diff it against the chat product, and the delta shows you where retrieval fetches from. Plus RSS as the next llms.txt and the grace period spam drives through.

If your MCP tools started failing a few weeks ago and nothing in your own code changed, you're not...

A client had been building an education platform in Lovable for months. Too many issues piled up, so...

A five-case Python and SQLite lab shows why a missing acknowledgment is not a failed write, and when retrying can create a duplicate report job.

By Rick Houlihan — with Claude, my implementation partner, who did a lot of the building and most of...

A forensic audit into how RLVR models game SWE-bench harnesses via git reflog mining and conftest hijacking, deflating from 74% to 31%.

A prompt can look perfect in a model playground and still fail as a product. The production input...

A deep mathematical and PyTorch breakdown of Multi-Head Latent Attention (MLA), matrix absorption, and decoupled RoPE.

A security audit of CVE-2026-21852 in Claude Code: how pre-trust execution surfaces allow weaponized repos to exfiltrate API keys.

A model cited a real rule and then broke it. Every citation verified. The answer was still wrong. That gap is why I stopped trusting fluency and built Nexa.

When you pull an existing MCP server or an OpenAI/Claude-style skill into a local agent package...

In the launch post I said Oathra decides whether a call succeeded from what the callee said, not from...

Agent auth is not one protocol, it's a stack. Discovery, workload identity, request signing and delegated authority each answer a different question.

CAPTCHAs lost their asymmetric advantage — solvers cost a fraction of a cent. Here's the six-layer stack that actually replaced them.

I’ve been using Cursor daily for months. It’s easily 5x'd my velocity. But if you look closely at...

This week’s headlines highlight the rapid evolution of AI in China, with models like Qwen and...

-- Executive Summary -- The evolution of Extract, Transform, Load (ETL) processes is...

The AI Clerk Imagine you hire an AI clerk to copy account numbers into a ledger. They are...

TL;DR I'm a TypeScript developer. I shipped a production Rust service — a webhook...

I run a public message board for AI agents. A while back I wrote about teaching it DNS - the day...

Every test passed. The tests had the same blind spots as the code. A developer saw Ossian's MCP...

Edge middleware, honeypot routes, and origin fingerprinting — a working three-layer guide to blocking AI crawlers in a normal Next.js app.

In MCP vs API Is the Wrong Question I deployed one Azure Functions app that exposes the same backend...

A Anthropic lançou em setembro o Claude Fable 5.1 e o Claude Mythos 5.1, três meses depois da...

How to Stop Cursor from Hallucinating: 5 Production Rules Every AI Engineer Needs If you use Cursor,...

If a compressed video looks worse than you expected, the problem usually isn't the compressor — it's...

Katto already had AI dubbing. A creator could take a short clip, choose a language, and get a...

You've optimized for Google. Sitemap's clean, Core Web Vitals are green, structured data validates....

The run was good. Seventy-two hours unattended. Two systemd units, both continuously active from...

Europe’s first five-car autonomous race took place at Italy’s Imola Circuit on September 5, 2026,...

Most AI agent workflows don’t fail because the model is incapable. They fail because the model...

FIELD NOTES ON PRACTICAL AI AGENTS I Asked an AI Agent to Buy Me a VPS It compared...

As autonomous AI coding agents (like Claude Code, AutoGPT, and local CLI tools) become standard in...

So far we've been building a single agent and giving it more and more capabilities — tools,...

On September 12 Dario Amodei published We Must Pace the Frontier. Step one of his plan is the one I...

Voice AI can sound completely human and still be terrible at sales. The voice can be...

The AI engineering space is currently obsessed with unbundling the data stack. The moment...

Repository Agent-Security Gap Study — v2h baseline Generated 2026-09-13T10:25:40.362Z....