I agree with this. I've been pretty critical of AI coding, but at the urging of some other HN posters, I shelled out a few bucks and started giving Claude Code a chance. After about 2 months of using it for various personal Python and C++ projects, my current problem with it is 1. how much babysitting you need to do to keep it on track and writing code the way you'd like it written, and 2. how much effort you need to spend after it writes the code, to clean it up and fix it. This tool would probably help quite a bit with 2.
I find for every 5 minutes of Claude writing code, I need to spend about 55 minutes cleaning up the various messes. Removing dead code that Claude left there because it was confused and "trying things". Finding opportunities for code reuse, refactoring, reusing functions. Removing a LOT of scaffolding and unnecessary cruft (e.g. this class with no member variables and no state could have just been a local function). And trivial stylistic things that add up, like variable naming, lint errors, formatting.
It takes 5 minutes to make some ugly thing that works, but an hour to have an actual finished product that's sanded and polished. Would it have taken an hour just to write the code myself without assistance? Maybe? Probably? Jury is still out for me.
Have you experimented with using a Claude.md file that describes your preferred coding style, including a few examples of what not to do and the corrected version? I haven't had complete success with this but it does seem to help.
Yeah in general I think agents are a mistake. People are desperately trying to make these things more useful then they are.
It's more useful as a research assistant, documentation search, and writing code a few lines at a time.
Or yesterday for work I had to generate a bunch of json schemas from Python classes. Friggin great for that. Highly structured input, highly structured output, repetitious and boring.
I still think vibe coding is a win. Sure, you can't turn it loose on a massive codebase, yet.
But in about 45 minutes I got 700 lines of relatively compact web code to use plotly, jszip, and paraparse to suck in video files, CSV telemetry, and logfiles, help you sync them up, and then show overlays of telemetry on the video. It can also save a package zip file of the whole situation for later use/review. Regex search of logs. Things linked so if you click on a log line, it goes to that part of the video. WASD navigation of the timeline. Templating all the frameworks into the beginning of the zip file so it works offline. etc.
I am not an expert web developer. It would have taken me many hours to do this myself. It looks crisp and professional and has a big featureset complexity.
(Oh, yah, included in the 45 minutes but not the line count: it gave me a ringbuffer for telemetry and a CSV dumper for it and events, too).
The last couple of revisions, it was struggling under the weight of its context window a bit and I ended up making the suggested changes by hand rather than taking a big lump of code from it. So this feels like an approximate upper limit for the complexity of what I can get from ChatGPT5-thinking without using something like Claude Code. Still, a whole lot of projects are this size or smaller.