We can do this today too (but definitely hopefully future LLMs make better architectural decisions). With Claude, I've been working on an application for the last 2 months. I didn't have a great vision of what I wanted when I started but I didn't want that to slow me down. The architecture is terrible - Claude separated some functionality into different classes but did a bad job at it and created a big ball of mud. Now that I finally have my vision locked down and implemented (albeit poorly), it'd be a great time to throw it away and start over. It'd be interesting to see the result and see how long it takes.
Just have claude (or gpt maybe) do an architecture review and request a multi-phase refactoring plan. This is probably better to do incrementally as you notice the balls of mud forming but it might not be too late. Either way, if it does something you don't like, `git checkout` and start over
> Once you try the models, you realise how good they are, and there is the second incentive. These things write working code and as the models get better and better, the argument that they make mistakes will get quieter and quieter until it fades away, like all high conviction opinions that turn out to be wrong over time do.
Is this true though? Will the models get better and better? I'm not a hater, but Sonnet/Opus generates terrible code albeit mostly functioning code.
I use Claude Code Sonnet and Opus for this and it works pretty well. Not perfect but good enough. At some point, I will have but to go in and tweak layout but like 99% of the functionality and layout is done for me.
I had claude build a backdoor command port in the Godot application I'm working on. Using commands, Claude can interact with the screen, dump the node tree, and take screen shots. It works pretty well. Claude will definitely iterate over layout issues.
Have you written this up anywhere? I have dropped my projects due to work/family commitments but see this as potentially removing some of the friction involved.
I interviewed at a company that used a simple project to screen candidates. It was implementing a cash register checkout system. The task was soo simple that I couldn't figure out what they were looking for. So I implemented the simplest thing possible. I got the job partially because they were impressed by my utterly simple solution. I helped evaluate other candidates given the exact same problem and it's amazing how some people dialed up the complexity to 11. None of them passed the screening.
reply