I just did something similar to bring mainline Linux to my Daylight DC-1 [1] [2], although possibly more difficult since I had to start from scratch.
I can guarantee the same amount of work, without AI, takes probably 10x or more time (I did it in the past w/ the Google Pixel C [3]).
Unfortunately it looks like pmOS is against AI [4], so I'll likely switch away from pmOS and never contribute a single line in the future.
Too bad, I was a huge fan [5].
In your case, it seems you had an automated (semi-automated, maybe?) feedback loop. In my case, I was the feedback loop :D which ended up being the bottleneck for some parts...
Yes! Removing the human in the loop speeds up the process. Models are better than the average SW engineer nowadays, so this isn't _that_ unsafe... and it really speeds things up
denysvitali · · focus · HN ↗
I can guarantee the same amount of work, without AI, takes probably 10x or more time (I did it in the past w/ the Google Pixel C [3]).
Unfortunately it looks like pmOS is against AI [4], so I'll likely switch away from pmOS and never contribute a single line in the future. Too bad, I was a huge fan [5].
[1]: <a href="https://daylightcomputer.com/product" rel="nofollow">https://daylightcomputer.com/product
[2]: <a href="https://x.com/DenysVitali/status/2091238391710888416" rel="nofollow">https://x.com/DenysVitali/status/2091238391710888416
[3]: <a href="https://github.com/pixelc-linux/documentation" rel="nofollow">https://github.com/pixelc-linux/documentation
[4]: <a href="https://docs.postmarketos.org/policies-and-processes/development/ai-policy.html" rel="nofollow">https://docs.postmarketos.org/policies-and-processes/develop...
[5]: <a href="https://blog.denv.it/posts/pmos-k3s-cluster/" rel="nofollow">https://blog.denv.it/posts/pmos-k3s-cluster/
vhaudiquet · · focus · HN ↗
denysvitali · · focus · HN ↗