stevex

Yeah, agree - the feat so far is that they brought up an entire suite of incredibly complicated apps from scratch in a week, and they seem to be tackling issues consistently.

There's a lot of depth in these tools, but the process seems to be working. Look at the issues, PRs, commit history and release notes. It's moving faster than a project with an "all code must be reviewed by a human who is responsible for it" policy would. Will be interesting to see if there's an upper quality bound.

You can almost tell the "era" that a solution was built in these days since things are changing so fast.

Mid-2026, we have very large context windows, and much smarter models than we did in 2024 when this was built. If I were to tackle this today I'd ask a current frontier model to work through the source data and design a hierarchy that would give it the ability to sift through the content itself by drilling down as it sees fit, and I expect it would nail that.

I don't think that's the direction this is going to take.

Replacing a mature app with an incredibly wide audience and a million use cases may or may not be possible, but what's actually happening is that people are making an app that does exactly what they want, and using it to solve their own needs.

Previously you might use Excel to take raw data from various places and analyze it, create charts, reports, extract findings. Now you can have AI write a script to produce the exactly report you want from the original data. No Excel required.

Photoshop is a good example for that, actually. How many people are just using ChatGPT or Gemini to get the image edits they want instead of reaching for Photoshop? I don't know if this is showing up in Adobe's subscription numbers, yet, but I expect it will eventually.

It's not true that there was no improvement in the rate at which models produced quality code.

Jan 2025 was Claude 3.5 Sonnet, Gemini 1.5 Pro and OpenAI had GPT-4o.

As someone who used all those models, as well as today's frontier models - today's models are a significant step up from those.

Doesn't it run over a USB-C shaped wire? If you're trying to understand things that plug into USB-shaped ports it seems at least worth mentioning.

Where does that UBI money come from if there are 50% fewer people paying taxes? That's the problem.

One thing Django has going for it is that the "batteries included" nature of it is perfect for AI code generation.

You can get a working site with the usual featuers (admin panel, logins, forgot reset/password flow, etc) with minimal code thanks to the richness of the ecosystem, and because of the minimal code it's relatively easy for the AI to keep iterating on it since it's small enough to be understandable in context.

Django + AlpineJS + HTMX is pretty nice.

"that obviously made no sense" is bizarre.

Waymo's driving people around with an injuries-per-mile rate that's lower than having humans do it. I don't see how that reconciles with "obviously made no sense".

I feel the same way. After 30+ years coding, I know what I want to build, but finding the time to work on it and the focus is harder than it used to be.

I had an Amiga disk image (*.adf) that I wanted to extract the files from. There are probably tools to do this but I was just starting with Claude Code, so I asked it to write a tool to extract the files by implementing the filesystem.

It took a few prompts but I know enough about FFS (the Amiga filesystem) to guide it, and it created exactly the tool I wanted.

"force multiplier of your own skills" is a great description.

I have an app in the store that's been doing reasonably well. Another developer released an app with the exact same name. (I'm not sure how, as the App Store normally prevents that). I filed a complaint with Apple, and they renamed their product, simply adding "Pro" to the name.

Search for any popular app name and you'll see the other apps trying to ride off the same search terms. Apple seems to be fine with that.

Where Apple will get involved is if you send them a properly worded legal request based on an actual trademark or intellectual property violation. They will act if they are compelled to, but only then.