Plus its just XML to its easy to derive flows programically

Conky forever!

I didn’t say that. I described the difference and stated a fact about distilled models vs frontier coming out of China. When you are distilling from a source without permission you get degraded results.

I also didn’t say that distillation is bad, I said they have narrower use cases. Nor did I say american companies are great.

But, please continue throwing your assumed biases out there.

There was never a question of if open models can match a frontier. Open just means you released the weights. The question is how they trained it. Most of the models coming out of China are distilled from larger commercial frontier models, and those are not the same thing. More situationally brittle.

Can be really good in narrow lanes, but not the same category at all. And that doesn’t show up in benchmarks.

Not familiar with this, but jumping on the opensnitch bandwagon. I use it, plus ufw, plus pihole.

Kill the DNS lookups, kill it at the network level of possible, and if it’s sneaky OpenSnitch catches it at the application layer.

Check out internet in a box. The Wikipedia foundation supports it. IMO that is also over engineered for my needs, so built a lighter weight variant.

That’s how they get wikipedia on this btw.

In my variant I have the complete English Wikipedia, a ton of official documentation on programming languages I use or might need to use, as well as calibre for eBook and pdf housing.

All running in docker containers, behind an nginx reverse proxy landing page.