To me this doesn't seem like a step towards those foundations, but another layer of of loss of agency. You can run "a" model locally, but you cannot make it locally (at least not for the purpose of just talking software into existence). You need to slurp up all the internet first, so to speak. And even if you could do that, you still depend on people putting new things onto the internet for you to slurp up. So is it really my software? What if it breaks or I want a new feature and AI corp nuked my account? How much did I learn during my time having it done for me?
And before anyone mentions it, I don't think the fact that I need a compiler and a manual and some example software to learn from is quite on the same level. I might be wrong but I would need some convincing.
You can also run a computer at home but you cannot even make a 486 from scratch at home, let alone something released more recently.
I agree on the SaaS side of the story, that's why it is so important to have open models.
Agreed, I wasn't advocating on using LLMs, even "open" or "local" ones.