I used some skills I picked up 20 years ago refactoring a huge and very messy codebase I knew nothing about and built a skill that allows Claude to do the same.
Seems to work really well by executing very small and very safe refactoring steps that don't break functionality.
Very curious to hear how this works on large codebases and in different circumstances and how else we can improve it so that refactoring becomes a solved problem.
I can imagine a bot that posts a "Show HN" for each of those ideas that points to a landing page generated with GPT3 and DALL-E and tracks traffic to figure out the best one to build.
I removed the worst of the cringy ones (e.g. AnalConnect for business analysts) and the "Inspiration" bit in each app can sometimes ring a little off, but I'm pretty happy with the result overall.
You're right, that's what the article is about, because that's easier. Finding paying customers and product market fit for an existing product is harder, and that's what I teach at growthlab.so.
You make a very good point. Whatever I manage to build is going to be experimental.
You're also right that therapy is a common way to create that self awareness, but it's not the only way. Some techniques work well without a guide like meditation and journalling, and others require a little guidance but nothing as in-depth as therapy (Byron Katie's Work and Sedona Method are two that I've personally found very effective).
Something to find the bugs, something to fix them, something to organize your thoughts, a tool for reflection. Oh boy, do I have a lot of ideas around this.
But we have to start with some basic awereness and emotional processing otherwise we'll get stuck in the same old mental loops.
That's a valid point. I think my approach to this does include fixing the problem and refreshing, at least for a certain category of inifinite mental loops.
Seems to work really well by executing very small and very safe refactoring steps that don't break functionality.
Very curious to hear how this works on large codebases and in different circumstances and how else we can improve it so that refactoring becomes a solved problem.