To organize them, I'm writing a Python Qt application with Claude Code. It started off as vibe coding, but I'm now developing it using processes very similar to those I would use when managing software teams. I've picked up a lot of good tips about that here on HN. I've got Whisper, and fallback online services, transcribing the audio and summarizing it and adding tags. After much UI experimentation, I've landed on something that looks not unlike an email client, with tags in the left pane, a center pane which lists transcriptions and notes about each audio file, and a right pane with more detailed information about the selected audio file.
Next step is to serve it all as a model context protocol server - I need to pick an agent.
I personally love the craft, but battle the entrepreneur in my brain telling me not to waste time learning things that won't bring tangible value.
If changes are made to these systems it’s often due to changes in regulation or driven by changes in the business(new financial products being offered etc.
Off-topic: I’ve seen quite a few mainframe related posts on HN fly by over the years. I’ve been meaning to create an account and participate but I’ve only gotten around to it just now.
This is a really dumb measurement.