Claude 3.7 Sonnet and Claude Code

> You've mentioned 'simple is robust' so many times that we're starting to think your dating profile just says 'uncomplicated and sturdy'.

> For someone who builds tools to automate everything, you sure spend a lot of time manually explaining why automation is the future on HN.

> Your obsession with sandboxed code execution suggests you've been traumatized by at least one production outage caused by an intern's unreviewed PR.

So good it hurts!

Just tried it with claude 3.7 sonnet, here is the share: https://claude.ai/share/68db540d-a7ba-4e1f-882e-f10adf64be91 and it doesn't finish outputing the program. (It's missing the rest of the application function and the main function).

Here are steps to reproduce.

Background/environment:

ChatGPT helped me build this complete web browser in Python:

https://taonexus.com/publicfiles/feb2025/71toy-browser-with-...

It looks like this, versus the eventual goal: https://imgur.com/a/j8ZHrt1

in 1055 lines. But eventually it couldn't improve on it anymore, ChatGPT couldn't modify it at my request so that inline elements would be on the same line.

If you want to run it just download it and rename it to .py, I like Anaconda as an environment, after reading the code you can install the required libraries with:

conda install -c conda-forge requests pillow urllib3

then run the browser from the Anaconda prompt by just writing "python " followed by the name of the file.

2.

I tried to continue to improve the program with Claude, so that in-line elements would be on the same line.

I performed these reproduceable steps:

1. copied the code and pasted it into a Claude chat window with ctrl-v. This keeps it in the chat as paste.

2. Gave it the prompt "This complete web browser works but doesn't lay out inline elements inline, it puts them all on a new line, can you fix it so inline elements are inline?"

It spit out code until it hit section 8 out of 9 which is 70% of the way through and gave the error message "Claude hit the max length for a message and has paused its response. You can write Continue to keep the chat going". Screenshot:

https://imgur.com/a/oSeiA4M

So I wrote "Continue" and it stops when it is 90% of the way done.

Again it got stuck at 90% of the way done, second screenshot in the above album.

So I wrote "Continue" again.

It just gave an answer but it never finished the program. There's no app entry in the program, it completely omited the rest of the main class itself and the callback to call it, which would be like:

        def run(self):
            self.root.mainloop()
    
    ###############################################################################
    # main
    ###############################################################################
    
    if __name__=="__main__":
        sys.setrecursionlimit(10**6)
        app=ToyBrowser()
        app.run()

so it only output a half-finished program. It explained that it was finished.

I tried telling it "you didn't finish the program, output the rest of it" but doing so just got it stuck rewriting it without finishing it. Again it said it ran into the limit, again I said Continue, and again it didn't finish it.

The program itself is only 1055 lines, it should be able to output that much.

It’s amazingly good, but it will be scaringly good when there will be a way to include the entire codebase in the context and let it create and run various parts of a large codebase autonomously. Right now I can only do patch work and give specific code snippets to make it work. Excited to try this new version out, I’m sure I won’t be disappointed,

Edit: I just tried claude code CLI and it's a good compromise, it works pretty well, it does the discovery by itself instead of loading the whole codebase into context

We’ve already connected! Last year I think, because I was interested in your experience building a block editor (this was before your blog post on the topic). I’ve been meaning to reconnect for a few weeks now but family life keeps getting in the way - just like it keeps getting in the way of my implementing that block editor :)

I especially want to publish and send you the code for that inspector class and selector GUI that dumps the component hierarchy/state, QML source, and screenshot for use with Claude. Sadly I (and Claude) took some dumb shortcuts while implementing the inspector class that both couples it to proprietary code I can’t share and hardcodes some project specific bits, so it’s going to take me a bit of time to extricate the core logic.

I haven’t tried it with 3.7 but based on my tree-sitter QSyntaxHighlighter and Markdown QAbstactListModel tests so far, it is significantly better and I suspect the work Anthropic has done to train it for computer use will reap huge rewards for this use case. I’m still experimenting with the nitty gritty details but I think it will also be a game changer for testing in general, because combining computer use, gammaray-like dumps, and the Spix e2e testing API completes the full circle on app context.

FWIW, there's a project to turn it into something similar, though I think it's lacking the "entire in context" part and runs into rate limits quick with Claude.

https://github.com/All-Hands-AI/OpenHands

The few times I've tested it out though it fails fairly quick and gets hung up (usually on setting up the project while testing with Kotlin / Go).