Trying to etch models into a chip is a dead end until we reach “peak” quality.

However, unless they include some kind of LoRA (low-rank adaptation) adapter onto the silicon, it severely limits the utility of whatever model or architecture they choose. Being able to modify the weights is way more useful.

Honestly, diffusion decoders are probably where we’ll end up some day. Not end there, but that’s probably the next logical step in the throughput chain.

General purpose compute is infinitely more valuable during times of great software improvements than highly specialized compute.

Things like Tensor Processing Units (TPUs) still aren’t ubiquitous yet, even though they’ve been around for 10+ years. They’re Too specialized to allow for reasonable flexibility on testing.

Did this one achieve some intense introspection just now?

I know what you meant (I have one for fish as well), but I chucked because you looked very enthusiastic about it!

The fish function for !! is super useful though

Honestly? I want that.

No joke, it looks like that may be the price for both units you can see there. Hard to tell from the sign, but it has two product codes with a + between.

Seems a bit steep for a single grand piano, and just about right for two.

I was able to beat him 3 or 4 days ago, after the rock pile thing wasn’t part of the fight anymore.

Overwhelming force: strength build, vulnerability , and the card that gives you strength when you lose health on your turn, combined with multiple cards that triggered damage, and a power that dealt 1 hp damage at the beginning of my turn.

Accept that you will lose a few cards and build redundancies.

I’ll look up my build later.

It’s only the standard for people who self host their llms and don’t have $500k to throw at hardware for GLM-5.1 or similar models.

I have qwen3.6:27b on my local hardware and it’s way better than I expected. I’m excited for the rest of the 3.6 line as it comes out, if they can keep up that quality.

This story is also a nothing burger. Generally, yes, Nvidia will suffer once chinas stack catches up (soon). By then whatever bubble we are in will have normalized one way or the other.

In terms of actually deploying this model, it doesn’t matter what hardware you’re using. VLLM supports almost everything with SIMD-type hardware instructions.

More competition will make everyone happy except Nvidia shareholders.