How “techy” are you? Do you have a couple of Raspberry Pis or similar laying around basically unused? Can you clone a git repo, open an LLM coding agent and get reasonable results out of the chat interface?
The ultimate goal is to get this 100% AI/LLM free, but for now the LLMs are still doing a lot of the heavy lifting of configuring the target devices to install the player.
The ultimate goal is to get this 100% AI/LLM free, but for now the LLMs are still doing a lot of the heavy lifting of configuring the target devices to install the player.
why don’t you use ansible for that, or even just some bash script? you could generate it even if you want
So far, every target is different - like the one with the 3.5" touch display built in, that has its own display driver module. Then there’s Windoze vs Ubuntu vs Raspbian OS, and the Pi Zero 2W has a few different considerations than, say, a Pi 4 or 5, and basically every place I have deployed this so far has had something unique that needed custom attention. Once that’s all worked out, sure, ansible or whatever, but customizing for each target isn’t something “last year’s tools” did as easily as the new agents.
Techy enough. I self host a bunch of stuff, have a few servers and am more or less comfortable cloning a git repo. I actually currently have 2 rasp pi’s begging for a job.
I’m just about to run my first test of the “echo mode” where each player plays its own local files, synchronized to one player’s play list (a few issues of delay/clock rate synchronization to deal with in that approach). After that, I discovered I need to do a project rename (I’ve duplicated another project name from 2021, so… time for a different name - on 100K lines of stuff…) then remind me and I’ll give you a pointer to the (new, renamed) repo.
45K of those lines are documents, specifications, testing results… It’s an overbloated mess bull-headedly pursuing a couple of arbitrarty goals of mine that not many other people have pursued (use of Disk At Once (DAO) audio files with passages defined as sub-sets of the file, 71 dimensioal passage “flavor” determination for next track selection using the now offline AcousticBrainz algorithms, deployment on 5-6 so far various hardware/OS platforms adds a bit as well…)
On the bright side: synchronization of 2 independent players is “coming together” - got some decent performance in the steady state case last night, now chasing the edge cases for faster convergence at startup, etc.
How “techy” are you? Do you have a couple of Raspberry Pis or similar laying around basically unused? Can you clone a git repo, open an LLM coding agent and get reasonable results out of the chat interface?
The ultimate goal is to get this 100% AI/LLM free, but for now the LLMs are still doing a lot of the heavy lifting of configuring the target devices to install the player.
why don’t you use ansible for that, or even just some bash script? you could generate it even if you want
So far, every target is different - like the one with the 3.5" touch display built in, that has its own display driver module. Then there’s Windoze vs Ubuntu vs Raspbian OS, and the Pi Zero 2W has a few different considerations than, say, a Pi 4 or 5, and basically every place I have deployed this so far has had something unique that needed custom attention. Once that’s all worked out, sure, ansible or whatever, but customizing for each target isn’t something “last year’s tools” did as easily as the new agents.
Techy enough. I self host a bunch of stuff, have a few servers and am more or less comfortable cloning a git repo. I actually currently have 2 rasp pi’s begging for a job.
I’m just about to run my first test of the “echo mode” where each player plays its own local files, synchronized to one player’s play list (a few issues of delay/clock rate synchronization to deal with in that approach). After that, I discovered I need to do a project rename (I’ve duplicated another project name from 2021, so… time for a different name - on 100K lines of stuff…) then remind me and I’ll give you a pointer to the (new, renamed) repo.
100k lines? are you sure you couldn’t outsource more tasks to existing tools?
45K of those lines are documents, specifications, testing results… It’s an overbloated mess bull-headedly pursuing a couple of arbitrarty goals of mine that not many other people have pursued (use of Disk At Once (DAO) audio files with passages defined as sub-sets of the file, 71 dimensioal passage “flavor” determination for next track selection using the now offline AcousticBrainz algorithms, deployment on 5-6 so far various hardware/OS platforms adds a bit as well…)
On the bright side: synchronization of 2 independent players is “coming together” - got some decent performance in the steady state case last night, now chasing the edge cases for faster convergence at startup, etc.