AI Intelligence Archive

Hotz says agent code is broken in ways that are harder to detect. Karpathy calls it bloaty. Same diagnosis: the risk is the reviewer who can't spot it.

The old problem: agents running as service accounts For most of the last two years, the...

Most local-LLM posts are written on machines with a good GPU. Mine doesn't have one, so I'm sharing...

German regional courts are beginning to draw a consequential distinction in disputes over...

How Coincide, an open-source Mac app, lets a thread move between Claude Code, Codex, Cursor, Grok Build, OpenCode and Antigravity without re-explaining the task.

AI Now Writes 75% of Google's New Code. 46% of Developers Don't Trust the Output. Nobody...

Pages cited in AI-generated answers were substantially more likely to begin with a direct response to...

Hreflang is often treated as an international SEO ranking tactic. Google’s newer framing points to a...

Foreword: After the AI Agent Goes Online, What is the Next Bottleneck? Welcome back to...

Introduction: Why Decoupling Prompts Isn't Enough? In the previous post [Agent Platform...

Introduction: From "Manual Prompt Tuning" to "Two-Layer Recursive Autonomous...

Every public profile you own says something slightly different about you. A step by step guide to treating your bio as source code, with one file, one tracker and an agent skill that checks the live sites.

Google has expanded its guidance on preventing user-generated content abuse to explicitly include...

Two defect studies (Bell Labs 2000, 11 projects 2013) found risky changes spread wide and grow files fast. Turn that into a reading order for agent diffs.

Your AI agent just wrote a perfectly reasonable Python script. Nice. The next question is where you...

I spent an afternoon convinced I had found a pricing bug. MiniMax H3 has six output tiers on...

A reader named arhancanli caught a problem in our last experiment: we had used overlapping Wilson...

Warning research shows people stop reading what they see often. Approving every agent command trains that reflex. Fence the agent so the rare prompt gets read.

Every TypeScript team has a rule about @ts-ignore. Ours does too, and it works: zero occurrences...

A reader found a bug in the script and asked whether an FP8 KV cache halves the long-context penalty. Computed: capacity is exactly 2x at every context, speed is 1% at 4k and 21% at 128k, and the crossover is where the cache read equals th…

A developer and father reflects on AI, independent thinking, books, and the example we set for our children.

Claude Code 2.1.309 stopped shell startup files running outside the Bash sandbox. Why zsh and bash run them at all, and a one-line trace to see it.

Every Monday, ExtraTime, my football quiz site, gets a health report written by a model. It reads the...

A practical playbook for Claude Code, Codex, Cursor and Copilot: manage context, cut token spend, and get code you can actually ship.

Five coding agents streaming into five panes all share one main thread. How xterm.js draws text, DOM vs WebGL, and a benchmark you can run.

There are a lot of ways to let a coding agent find code now. Plain grep, a language server behind...

For about two months, the first thing I did every morning was refresh an inbox, looking for a word...

Google, OpenAI and Microsoft are moving toward a common way for website owners to express whether...

A README file in your ~/Downloads folder should not be able to expose your SSH keys. A calendar...

Green tests from an agent prove the tests run. Mutate only the files its branch changed with StrykerJS and read the survivors as untested lines.

DeepSeek open-sourced Super-agent, a GitHub coding agent. Unasked work defaults to observe mode, and its workers run with full access as your OS user.

DepForecast: A Weather Forecast for the Ghosts in Your node_modules (work in...

This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 4, "Ghost in the...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

AI coding agents can write code, modify files, and report that a task is complete. But a...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...

Real ghost reports printed in American newspapers between 1846 and 1933, each shown with its original scan and the exact words behind every fact. Never a retelling.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...