I think that no matter what happens we’re going to foot the bill. There’s no way in hell these assholes will ever face consequences of any sort. They already destroyed consumer electronics markets, and will bring the rest of the economy down with them if they fail, but they themselves and the parasite investors will never lose. We’ll have to pay…

I’m not seeking to justify their actions, but explain why the change seems to have happened around that time. I’m not convinced it’s totally on gen X to have that sudden change, but more that the entire population was affected by the explosion of propaganda

Other things that have changed in the same time frame is the explosive growth of Reich wing broadcasting. Rush Limbaugh and the like coming to reach millions of people and then the birth of fox news. That has made things much worse in the last 40ish years

Narrator: they did in fact take it.

It has been some time since my initial comment so at the time I was mainly using LM studio. Qwen 3.6 a3b is the MOE and it does work well on my card, but the dense model that is more intelligent/capable is the Qwen 3.6 27b which doesn’t fit on the card and does get offloaded, but offloading cuts the speed down to like 1/tps.

I have since found a version of the 27b model that is “quantized,” for lack of a better term, differently and has to be run through TabbyAPI which gets back to 30ish tps. It can’t offload so it must fit fully on the card which keeps the speed high. Might be worth a look if you’re interested, the only downside is that with my 16gb card the context limit has to be kept pretty low ~40k if I remember correctly

Motherfucker is going to do an 18/22!

“OpEn WeIgHt MoDeLs ArE uNsAfE, oNlY wE cAn Be TrUsTeD!”

JFC… Sorry the billionaires decided we’re not going to address climate change so they can get more rich. They’ll have proper air conditioning too, you’ll have to get used to it. Have you tried having a sauna?

It’s literally what I tell my friend who seems to be convinced they’ll suddenly be altruistic… Like dude, you’re saying the very same people that fight any form of taxation whatsoever will magically be ok with “giving away” their wealth to people who do no work? They’d rather start a new company to make more money that just films nation wide “bum fights” as they treat us as entertainment, fighting over a chance to eat, than they would give anything for a UBI.

I believe BMW and others are already operating humanoid robots that work in a factory setting doing tasks a typical machinist would do right now.

Just imagine in 10+ years when the frontier agent models get optimized enough, or more effectively streamed into the robotics and the robotics are robust enough to handle “heavy lifting” tasks. I don’t think there is much some combination of AI and robotics can’t do. Other than suffering the soon to come mass poverty… They’ll never be able to do that.

Literally my first thought when reading that headline

every year I get a letter from my health scam insurance company that essentially says “due to the law (that we’re going to eventually pay the right politician to get rid of) we’re informing you that our rates will increase by 30% next year.”

Every year 30% more.

Thanks for the tip! I do have a 5080 so I’ll have to look up exllamav3

I can also vouch for lmstudio. If you can get Hermes running on Linux I would suggest trying that as well. It connects to lm studio and you use Hermes to communicate with the model. Iook into it as there’s a lot to it, I’ve really been enjoying using it so far it even learns how I like to create tasks and I’ve stopped having to ask it to delegate certain tasks, it just knows to do it and to break down the tasks so my fairly context starved local model can handle it.

As for a model, the Qwen 3.6 family of models do really well. I’d suggest the Qwen 3.6 35B a3b probably Q4 depending on your hardware. It’s large, but because it’s a mixture of experts model only 3b of experts are kept on vram at any one time so it stays fast. Qwen 3.6 27b is the smarter “dense” model, but trying to stay with Q4 for quality it becomes too large for 16GB vram and for me runs at like 2 tokens per second lol

The issue is that they became part of everyone’s 401k so the bootlickers and greedy fucks in Congress will tell us they’re 100% essential because if they fail you lose your retirement.

I hate this system… Redistribution of wealth for the rich, rugged individualism for the pleb.

Like Meta, Google, and Palintir.

You named all US things that the oligarchs profit off of. They’ll never ban anything that they profit off of. They want to ban the Chinese models because they compete with the corps that these fucks are invested in. It’s always greed when it comes to us political decisions

Thanks for the tips! What I had started doing the other day was having one session where it reviewed the code and created a document explaining what the program did in technical detail and then in another session I asked it to review that document before attempting anything with the program. Agent programs and harnesses are the next thing I need to start learning for sure.

It’s the q4 quantization, but it requires 20+GB vram and my 5080 only has 16

That’s what I generally use. I wanted to see if I could use the 27b to “review” what the 35b put out. The 35b has been working pretty well, but it’s not very thorough. I asked it to make a program and then 27b was like “this is a skeleton, there are folders but no contents.” Lol