I think point 2 will change once this becomes common. Once there is demand Home Depot etc are the perfect place to sell individual medium sized panels.
Hopefully it won't take 10 years for this to become easy.
Yeah, I too long listened to radio after being a DJ in college. WXRT in Chicago was my go to. It's still running and I just listened to maybe 30 minutes: so many ads! I do enjoy the DJ banter and local references but with all the ads it ain't worth it.
Define a MVP (minimum viable product) which is the minimum functionality that produces something useful and/or interesting. Implement that. I use Strava et al. myself. I'd say the MVP would include recording and storing and exporting the tracks. Then add your real-time team tracking feature.
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.
> 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.
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.