As someone who took years investing in a system to easily spin up indie projects before vibe coding was coined. It’s been crushing to have built quality projects that are now swallowed up by a tidal wave of AI slop.
It may or may not be a great time to be a popular indie dev, but for the less known folks - it’s a lottery
This is similar to how I’ve transitioned to learning new programming languages. I used to build stuff to learn. However, with AI assisted coding I don’t have those organic moments I’m stuck and need to search online for the answer.
My learning process now uses Claude Code to serve as a tutor that creates bite sized lessons writing parts I want to re-review, found confusing, what lessons were reviewed and what is next into a long lived CLUADE.md file.
I’ve noticed Claude Codes sandbox mode works with MCPs. With CLIs I’ve rain into permission issues. CLIs also need reminding about whats available unless references are baked the context window.
This weekend I was trying to figure out how I can use my smart meter’s electricity data. I had a poke around MQTT explorer and realized I could see personal data points out in the open without encryption across a plethora of devices.
I would have liked to see statistics on study session length eg. average duration. Also how long you typically spend creating per card and how many you created this year.
That information would help us all better assess whether the time spent on a spaced repetition flashcard system is justified
I’ve done something similar recently, using speaker diarization to handle situations where two or more people share a laptop on a recorded call.
Ultimately, I chose a cloud-based GPU setup, as the highest-performing diarization models required a GPU to process properly. Happy to share more if you’re going that route.
