1,062 karma · joined July 14, 2022
That said, I think the hardware is totally capable they just don't have a layer to run win32 or Linux apps natively (like proton for m series) so they'd have to commit to what valve is doing for linux, for macos
Either way, I don't do what you suggest. I have self-learning rules and have the models build a well-rounded API engine once, then re-use it with query scripts through skills. Its portable and flexible in many environments.
There is a rule to always use this skill and then track notes in a version file. Then back it up in a share folder or external drive.
Skills have made my tools immensely better, cheaper to use and faster. I've also added to it that it should write scripts it can just use in the future to do tasks like query information it needs to answer questions.
I wish there was a better way to share these over a team but I haven't taken that time yet.