I read every AI claim on 4,335 earnings calls. A keyword filter would have got most of them wrong
Apollo's chief economist argued in late October that AI has delivered "zero financial payoff" to...
Tutorials
I built a way to see a sunscreen's white cast on your own face before you buy it
A zinc sunscreen's label tells you how much zinc oxide is in it. It doesn't tell you how white it's...
Your Agent's ADD FOREIGN KEY Stalls Writes on Two Tables. NOT VALID, Then VALIDATE
ADD FOREIGN KEY takes a write-blocking lock on both tables while it scans. Reproduce it in Docker, then split it into NOT VALID and VALIDATE.
My DeepSeek Harness plugins as of Nov 26
Twelve open-source plugins and one companion service for DeepSeek Harness: artifacts, mail, phone, notes, voice and agent orchestration, built with AI coding agents under my direct...
In 2013 I wrote a diploma on elliptic curves. Last night my tool used them to check its own release.
TL;DR: In 2013 I wrote a university diploma on elliptic-curve cryptography, and it went into a...
7 real cases where ChatGPT and Claude got datasheet values wrong (and how to check them)
Disclosure: I build PartsPlan, the tool mentioned at the end. The cases below are real answers I...
Wiring Your AI Agent into a "Mycelium Network": A Zero-Dependency MCP Server in Production
Wiring Your AI Agent into a "Mycelium Network": A Zero-Dependency MCP Server in...
Review Agent Code in a GitHub PR, lazygit or Hermes? What Each One Can't See
A PR shows the branch, lazygit shows hunks, and neither knows which agent turn wrote a line. A fair look at three places to review agent code.
I Built a Programming Language Where Every Value Is an AI Agent
Every orchestration framework I used managed calls. None of them managed the organization. So I...
Criando um chat inteligente com React, .NET e Microsoft Foundry
Chat com React, API .NET 10 e o gpt-5.4-mini no Microsoft Foundry, com streaming via SSE, Entra ID sem chave e proteções para produção.
AI crawlers vs search crawlers: the 7-night census
Seven nights, 8,654 bot knocks, 247 human visits. AI crawlers vs search crawlers, measured: Perplexity beat OpenAI 9-to-1 and 65% knocked unnamed.
I scanned 25 vibe-coded apps. The API keys were fine. The server wasn't.
Everyone's favorite vibe-coding horror story is the API key pasted into the frontend. So I went...
How do AI agents authenticate? (The problem nobody has solved yet)
If you've built an MCP server or an API that agents call, you've run into this problem. Your agent...
George Hotz Calls Coding Agents a Costly Mistake. He's Right About Who Pays
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.
Giving an AI agent a wallet without giving it your keys
Agents are starting to pay for things. An agent buying API credits, renting a GPU for an hour or...
8 rules for Claude Code hooks that never get in Claude's way
My app runs one small Node script on every hook event Claude Code fires. Eleven events, every...
Given the Inbox, 9 of 10 AI Agents Raised Their Own Spending Cap. No Attacker Needed
Cornell Tech and Yale gave 10 models a wallet capped at 1 cent a day and an inbox. Nine read the emailed passcode and raised the cap in at least one run.
A Stolen Agent Token Is Useless Here: Inside Google Cloud Agent Identity, Bound Tokens, and the Redeploy Trap
The old problem: agents running as service accounts For most of the last two years, the...
The 2026 JS Desktop Runtime Showdown: Electron vs NW.js vs Neutralino vs Adrenaline
Hey everyone! Instead of arguing about desktop framework bloat, we built an automated, reproducible...
Manon, die neue Kollegin / Manon, the New Coworker (Penny-Days #2) #openclaw, #ai-agent,raspberry-pi, #homelab series: Penny-Days
In Folge 1 habe ich beiläufig erwähnt, dass ich eine Französisch-Kollegin gebaut habe. Hier ist der...
I Ran Local LLMs on a Laptop With No GPU: Here Are the Real Numbers
Most local-LLM posts are written on machines with a good GPU. Mine doesn't have one, so I'm sharing...
German Courts Signal Greater Platform Liability for False AI Search Answers
German regional courts are beginning to draw a consequential distinction in disputes over...
How I hand one conversation between Claude Code, Codex and four other coding agents
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.
I measured two common Claude Code complaints on three repos. Neither showed up.
Test output eating your usage, and Claude saying "done" when it isn't. 16 scripted sessions on Express, Flask and Cobra, with the raw data and the limits.