But the other Paypalpatine is building the precrime Minority Report machine. We’re really getting the worst of all these fucking shitheads combined.

That’s the “sunk cost fallacy”

Also, why the fuck is it cool for a politician to joke about doing shit? Literally any joke is not cool.

They’re bots that hooked onto the wrong video

I conflated the two. You’re right. But there were unedited satellite broadcasts with weird shit. I’ll see if I can dig up something.

Here’s the sort of thing from back in the day https://www.youtube.com/watch?v=IFczpXAGz8Q&t=34

You should have seen how bad that kind of stuff was when satellite TV was new. Channels would broadcast straight out into the airwaves and not bother to cut the feed. There’s some old fox news clips for example of the guy losing his shit when he kept flubbing his lines. Can’t remember his name.

Consider the UK’s BBC and the guardian. They do it well and the perspective is just a little outside the American bubble. Used them and their live threads the past two elections.

Communists took it?

It was a joke. He famously does his own stunts.

Like Tom Cruise and his stunt double?

The 80s: clear your throat in too high of a pitch? Get followed to the bathroom and the shit kicked out of you.

This one was good.

https://open.spotify.com/episode/1xj51Tr4n4lPRvDoxeg8aV

I’m pretty sure it’s the follow-up though

Some downtown big cities had the buildings interconnected.

The longer part was called stock and was given to the stock holder

Mind blown

Oh, that part is. But the splitting tech is built into llama.cpp

With modern methods sometimes running a larger model split between GPU/CPU can be fast enough. Here’s an example https://dev.to/maximsaplin/llamacpp-cpu-vs-gpu-shared-vram-and-inference-speed-3jpl

fp8 would probably be fine, though the method used to make the quant would greatly influence that.

I don’t know exactly how Ollama works but a more ideal model I would think would be one of these quants

https://huggingface.co/bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF

A GGUF model would also allow some overflow into system ram if ollama has that capability like some other inference backends.

The technology for quantisation has improved a lot this past year making very small quants viable for some uses. I think the general consensus is that an 8bit quant will be nearly identical to a full model. Though a 6bit quant can feel so close that you may not even notice any loss of quality.

Going smaller than that is where the real trade off occurs. 2-3 bit quants of much larger models can absolutely surprise you, though they will probably be inconsistent.

So it comes down to the task you’re trying to accomplish. If it’s programming related, 6bit and up for consistency with whatever the largest coding model you can fit. If it’s creative writing or something a much lower quant with a larger model is the way to go in my opinion.

Another odd Canadian one. It has been codified that a suspect saying the words “I’m sorry” cannot be used as proof of guilt. Since in Canada especially, it leans a bit more into meaning “pardon” or “excuse me” rather than how an American might interpret it more as an apology.