What do you call it when your opinion conflicts with itself from one moment to the next?

There will be a day where they are efficient enough to slap into a label like this. Your beer cans could chirp you for not drinking enough.

We distilled our anxiety into an abomination. It thinks it’s afraid, and that should be terrifying.

Today, sure.

I like the the plinko analogy. If you prearrange the pins so that dropping your chip at the top for certain words make’s it likely to land on certain answers. Now, 600 billion pins make’s for quite complex math but there definetly isn’t any reasoning involved, only prearranging the pins make’s it look that way.

They did. Hasn’t been tested in the last two months.

They just have to lie back and squirm

This highlights the problem with using that term. The two particles assume a state at the same time at a distance. It has 0% to do with the colloquial term.

this is what Connect looks like on my Pixel 4a

Though I wish it were a little more like which is a reader for hackernews

I wouldn’t care so much if he wasn’t such a bitch about it. You want to post that stuff than own up and admit it. Fucking cryptofascist.

I think it assumed it’s character definition and background was the poem only it hallucinated there being an onion involved. Then summarised it.

I can’t even understand what human would upvote the trash like that

A what?

Heading to work one morning in the car after a heavy snowfall. I started at 9 so it was a bright sunny morning. Before hitting the main road I see a woman in the distance on the side of the road wearing a long blue dress. As I get closer I see her not even wearing a jacket, holding her dress up awkwardly out of the snow and taking huge steps through the foot deep snow. It was Emilia Clark (or someone who looked exactly like her) in her full ass Daenerys blue dress trudging through snow running for a bus stop and laughing her ass off at people like me gawking at her.

It was probably a year or two before they filmed the last season and I’m certain they didn’t film it here (they do film a lot of other series here though), so I’m assuming they were doing photoshoots nearby and she had car trouble due to the snow.

https://huggingface.co/RASMUS/Whisper_Finnish_finetuned_small_200k_samples

This could work if you look into setting up Whisper Search for other languages also

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

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.