It was a joke. Most people don’t know the difference between upload and download or push versus pull.

Internet providers would measure how much data each sender pushes to their customers

But what if my customers are pulling data rather than me sending data?

Saying nothing would be a good start.

No shit. I’m writing my rep and demanding they find someone else. That secret meeting he had with Kushner tells me that he probably put his dick somewhere it didn’t belong and they’ve got evidence on him. Hakeem will sell us out, if he hasn’t already.

Find someone else!

Try this out https://www.youtube.com/watch?v=4Hvkv_I8QDE

This is where I learned of it, but I’ve also hooked up unsloth desktop to the same obsidian knowledgebase. This way the long term memory persists across my LLM client tools. Right now I have it keep track of me and my preferences, my wife and her preferences, home lab architecture and documentation and technical project information for me and my wife.

Italian is a beautiful language, probably my favorite one.

As far as your post is concerned, I’m using qwen 3.8 27B as my main local LLM. I actually do have it push code to a github repo. Mainly because I have no real interest in learning the code it is writing, I’ve always been a back end and data person and I’m having it write web stuff. One thing I do a little differently is I make sure the model writes documentation up front and then at the end and also any steps it discovers, that it should remember into an MD file. This is so it doesn’t make the same mistakes over and over.

I also make sure it writes instructions for itself(or another model) and I will sometimes have another model check its work.

I have started implementing long term memory with obsidian as its “second brain”. This way I don’t have to keep explaining who I am or what we’re doing, what machines are available, what my preferences are, etc…

I think in a few weeks I’ll be able to grab my phone and start giving it tasks to do, using Hermes.

Nice write up. I appreciate you taking the time to share.

No. As a consultant I’ve seen hundreds of businesses. There’s a ton of inefficiency. Check out David Graeber’s book, “Bullshit Jobs”. He details a lot of inefficiencies throughout the whole system. It’s a real eye opener.

It’s clearly written by someone who is not a native English speaker. I noticed that in the first paragraph or so.

Or do you think an LLM would write “…i can finally say i am quite satisfacted”

This is not to crap on OP, I’m very impressed with their command of English.

I always laugh when people tell me that businesses are naturally efficient. They clearly have not worked for large companies. Or they are sleepwalking through life, seeing only what they want to see, like far too many people.

And they’re probably making mistakes too. It’s amazing how many data merges happen out there that result in wrong data. Not too long ago my credit card company sent me a new card overnight because of fraud, but they didn’t send it to me, they sent it to a family member of my ex wife’s. I’ve been divorced over 20 years now and I never even lived there. But the CC company decided to merge their data with other data and fucked up somewhere along the way.

That’s one of the ways the rich exploit the legal system.

These are great stories. Thanks for sharing.

I wonder if they targeted users they couldn’t tie back to real identities. I never used an account tied to a real identity or a real email address and all of my accounts were banned for pretty innocuous or specious reasons.

One was banned for advocating violence against women, because I called Kaitlyn Jenner an attention whore. One was banned for saying Luigi is a hero. Of course all attempts at appeals were ignored.

The biggest issue in my home is not the mainstream streamers but things like Kanopy and Hoopla(public library offerings). If I can’t get those, then it’s a dead project before it begins.

Thanks for the root guide, I’ll look into it.

The best option is what the subject of the post is about and just tear down the firmware and see what it does. This is happening now and is the best answer.

I don’t know, I think an open source board replacement would be good too. I’d prefer that, actually.

Hell, if I could make a decent replacement for Roku and plug it into my TV, I’d open the TV up and disable the WiFi altogether.

Summarizing a discord channel into a usable format would be an excellent use for an LLM.

you’d be astonished by the assumptions that are made about the public…

Please provide an example or two. I’d like to be astonished.

Why cant WE be our own government?

Because most of “we” are checked out dummies who are easily manipulated by unscrupulous entities. And the more money you have, the more dummies you can manipulate.

More than anything, we need to stop buying this shit.

Or we can pull together and design boards as drop in replacements for the circuit boards in the SmartTVs. I’m shocked at how cheap it is to get custom boards printed these days. Since SmartTVs are sold at a loss with the intent of making even more money by selling your data, replacing the hardware in the device should still end up being cheaper than the cost of an unsubsidized TV.

With the AI tools available for designing boards now, it shouldn’t be terribly difficult for those with the right skills to do this.

They could make these data centers quieter using ground source heat pumps, they could also build up solar farms to power them.

But they won’t do that unless they are forced to.

It’s not unreasonable to insist that companies be good neighbors. Especially when those companies are in the business of taking your jobs away and creating a surveillance state.