I'm in Sydney this week with @RealGeneKim, getting ready to conduct a week of Vibe Coding workshops, compliments of Commonwealth Bank of Australia, our generous sponsors for this trip. I realized this morning chatting with Gene that we've identified a bunch of new and very

This is the first UI for Beads that I could see myself using. Pretty clever. And it's a Terminal UI!

New article on Beads Best Practices:

I just finished writing "Cheese Wars: Rise of the Vibe Coder", which explores the important question of whether Big Tech giants would mind if most of humanity turned into cheese wheels. The post also offers tips for getting AI on your side, once it's smarter than we are.

It’s giving minimum effort, maximum vacation vibes.

I honestly love the way the ads look in our TUI.

I wrote a fun little post called Beads Blows Up:

I've just published a little article about a principle I've been using that I call ZFC (Zero Framework Cognition). I've found it to be a useful guiding principle in AI-enabled applications.

I wrote a piece called Beads for Blobfish about how Markdown files are invading our planet and destroying all sentient life. I propose Beads as the bulwark.

I've written another article about Beads, my drop-in memory upgrade for coding agents. https://t.co/APkanQfxS9 I vibe coded Beads from concept/design to a thousand GitHub stars and fifty forks, in just six days. How do I know it's the real deal? How do YOU know? It's simple.

I just released Beads, a drop-in cognitive upgrade for your coding agent of choice. https://t.co/dl9cQO0Jjo In a nutshell, it is a magical 4-dimensional graph-based git-backed fairy-dusted issue-tracker database, designed to let coding agents track all your work and never get

Hmmm, after a lot of drama, it seems the culprit may have been an "npx lint-staged" pre-commit hook that was reverting all changes, including all attempts to disable the pre-commit hook. I have to say, I really liked Node and TypeScript before I tried using them.

Where is August Alsina? His Rise Was Followed By Scandal

I tried Claude Code today for the first time in a month or two, and almost immediately it seems to have found a bug in itself.

Check out my latest article: Playing Chicken with AI https://t.co/bO9pLe0yVr via @LinkedIn -- it's about you!

This is correct. We had this same reaction in the 1980s & 1990s when compilers generated assembly for us. We hated it. Looking at the generated code made us puke. It got better.

I've been using up to a dozen coding agents at a time for nearly a week straight. Just added my 13th. All working on the same project. It worked amazingly up to about 200k LOC, and now they've begun savagely overwriting each other's work rather than try to deal with merge

OK, here's a new one. I lost a whole day in one coding agent workstream (which is like lost weeks in pre-2025 time) because, get this... It had created a security system preventing my target application from running any tools, but it forgot to tell me about it. It also forgot to

All-in-one solution - Org invites - RBAC - Subscription billing Clerk helps your SaaS grow and monetize faster.

Here's a bit of coding agent magic fairy dust for the day: Don't tell the agent to do something. Tell the agent to _begin_ doing something. The LLM will, on average, make wiser choices about how much work to bite off.

This morning I helped @AmpCode teach itself to create and edit Google Slides presentations for me. Here's a snapshot of early stages; later snapshots are too polished to be interesting. Amp writes Python code to invoke the Slides API for slide CRUD, then MCP + Playwright to check

https://t.co/2RwWCjBCXQ

I came to the same conclusion as @michaelshuffett -- you hit a cognitive ceiling around 3-5 parallel workflows. Sometimes 2-3 will bog you down, and sometimes you can hit 4-5 streams at once, but either way you're always the bottleneck. You. Not them. And yet 95-99% of the time,

Find a fave cosplayer!