spent some time last week adding metadata to my mp3 music obtained with yt-dlp. used musicbrainz Picard.
I’m actually really surprised how comprehensive that database is, and how easy it was to manually tag the tracks that didn’t get picked up automatically.
bringing you joy is its purpose, and that is valid.
Claude is geared more towards enterprise companies, anyway. I think you went over pretty succinctly as to why: they can afford the extra resource burn.
pretty much the way I use AI rght now is similar to how you see the near future of your use.
its pretty useful for getting through writers-block type scenarios sometimes because of that, but past the initial stages of the project the usefulness declines dramatically.
I’m still not seeing any real ways of removing the human in the loop, especially for the review process.
thanks for your writeup. I didn’t read the original but this one was fun to read through.
this looks like an awesome project, and I appreciate how you went over the ways AI helped and hindered your project at the end. its really hard to get honest feedback about AI from devs IRL right now, everyone keeps saying they have silver bullets in their workflows and I feel like the crazy one for not being able to figure it out.
looking forward to giving AC a shot!
this is shockingly ambitious from the flipper team. wow.
I don’t have experience with ARM development, but IMO that seems like the field that would benefit the most from this project. its also where I see the most pushback occurring.
very happy they’re opening this up. they built a good community with the first flipper, I’m sure there are tons of qualified people willing to contribute to this one.
do you have a portfolio I can browse? I love this