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.

Agreed. And we can easily bridge existing net to alternative transmission mediums while the existing net allows. Providing an easier time for others to adopt. I run a reticulum node as well.

Can't. Its too powerful to release. But I built it by combining other opensource projects, osint playbooks, and removing any moral guardrails. Hence the dangerous part.

I didn't post to flex, just to point out that its not a future state. This is something that already exists. If I built it, at home. Using open source tools, what do you think palantir can do

Its already possible. I built a tool to investigate myself. I purge my info from the web. I better the tool, find more, purge more. You would not believe what I can find.

Did anyone mention that huggingface will quanticize for you? Its like one button push.

Navidrome user here as well. I use feishen as my Linux and windows desktop client. Big fan of both.

As others have said, api is just the standard, so it gives you a lot of options

So Firefox has tab sandbox isolation built in, but its cumbersome to use. When I started using waterfox they suggested a Mozilla add-on that made the feature more available. Have to go look at it, container something.

That being said, you can explicitly set URLs to sandbox groups, which is pretty handy when you want to keep cookies buy you don't want them shared necessarily across sites.

Combined with noscript and ublock I have fine grain control of what I allow to run on sites and what cookies I'll take.

So for sites I regularly visit I have it all preconfigured.

Then I just use a sandbox for random browsing.

Ticks all the boxes for me, without needing separate browsers for "everyday" tasks.

Been using duckduckgos browser. No idea how that stands up to iron fox, but it was a lot better than chrome or vanilla Firefox, which is what I was using before lol

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.