One small correction: Andrej Karpathy coined the term "vibe coding" in February 2025, a year after leaving OpenAI for the second time. He joined Anthropic in May 2026.

One of the foremost tasks of art has always been the creation of a demand which could be fully satisfied only later. The history of every art form shows critical epochs in which a certain art form aspires to effects which could be fully obtained only with a changed technical standard, that is to say, in a new art form. The extravagances and crudities of art which thus appear, particularly in the so-called decadent epochs, actually arise from the nucleus of its richest historical energies. In recent years, such barbarisms were abundant in Dadaism. It is only now that its impulse becomes discernible: Dadaism attempted to create by pictorial—and literary—means the effects which the public today seeks in the film.

Every fundamentally new, pioneering creation of demands will carry beyond its goal.

Walter Benjamin, The Work of Art in the Age of Mechanical Reproduction, 1935 https://web.mit.edu/allanmc/www/benjamin.pdf

Edit: to put a finer point on it, AI art like this is, through it's rigorous application in almost every previous medium, showing that there is a demand and energy for a new art form that depends on the changing technical standard and capabilities that AI has introduced. I don't know what it will be, but you can see some of the edges of it with how it is making waves in all the other mediums.

Well, they could just share their prompts :)

There's a tangible quality to mechanical creations. Miss that hands-on feel when debugging distributed systems all day.

Yes! That is what I came to say: it's interesting, but I can't contextualize the workflow he describes without knowing the the quantity of tokens involved and their retail cost.

I started by creating a new Claude Project. Projects are becoming a layer that spans Chat, Cowork, and Code; you can think of them as sitting above domain-specific concepts. You talk to one Claude with the ability to spin off additional sessions, share files and memory between them, and supervise the entire fleet of Claudes to achieve goals.

Earlier this year, I would have joked that I get a lot done by telling a bunch of Claudes to do work. Now, I’ve put one Claude in charge of each of my projects, and in turn, that Claude knows how to manage tasks, investigations, and threads. We’re talking more about goals and less about how to achieve them. My little Project setup.

Every thread gets its own computer in the cloud, where it installs whatever it needs (Blender, FFmpeg, Playwright), checks its work with screenshots from a headless browser, and publishes a private preview page for me to click through. > All threads share one folder of files and one memory. Claude is smart enough to write down decisions I made in memory and makes sure newly started threads follow them without me having to repeat myself.

I must be missing the setting in my claude/claude code - how does one do that?

A project is just a custom prompt and some files you can attach.

Claude code is the same thing with some .claude files, and the folder directory is local to your machine.

Where is the ON switch for all of this? Showing the method and steps and prompts would be more useful than this post.

pointing out differences between the thing I worked on for 24 hours and a room designed painstakingly by hand over weeks.

I went in expecting something handmade, and instead got something that was Claude-made. This doesn’t make me feel good, or feel user-centric. Now we’re throwing Blender into a webpage and serving it client-side rendered to users?

If anything, all of this feels more like bloat rather than something personal. It’s art for Claude’s sake. It’s not telling a story. Even on the actual blog post, the dropdown table of contents displays how long it takes to read each section. It feels so disconnected because it’s possible to throw a feature in, but is it really necessary? Maybe I am getting better at determining AI-made UIs, but all of this feels incredibly artificial.

Lastly, for all of the parallel QA checks and threads, all of the header links besides the “About” page throw a 404 at me. It’s almost ironic.

Besides the About page and this one blog post, all other links on the site are broken. There’s no need to feel defeat.