Carl

And so it depends on what you do.

I think there was news where they're just testing the infrastructure because the whole goal is to give Cerebrus to all the models, to run it off Cerebrus, but they have to test it first.

Can you think of all the things you're doing

at that speed it do like the the like just the concepts of like forget like sure it'll take you a little bit longer but like 29 seconds when because what i've been doing and you get rate limited a lot right now i'm at the max plan and i you get rate limited like there's a separate rate limit just for codex spark

like on codex you have everything else it goes through but on spark there's another little like yeah it's um but what i've been doing is i've been doing plan mode on um whatever model and then i would execute in codex and it would be like this is ridiculous and then i would test it against like opus i would test it against that and what i'm building i'm like holy like and you can only do so much there's only so much they can give you

But I am very excited about Cerebrus being provided to everybody because what you can do with it is that's pretty amazing, right?

Like 29 seconds versus just 5.3 seconds.

building that in two minutes but how much of that difference was the difference between 5.3 codex not spark and spark is it purely the servers thing or is spark purely purely the server now the only thing that they didn't give spark so it isn't as the reasoning isn't as high as 5.3 uh codex

um just regular codecs and i think in the discord they were saying it's like the look the ford is to give it to 5.5 like eventually i don't know when but any of the higher models that's where they're providing it the only question is who gets it

Because the level of compute you need at that speed is ridiculous.

So we'll see who gets it.

But I think most people have never tried it, have never done anything with that at that pace, at that speed.

It is...

It's kind of crazy.

I did videos about it, but no one, unless you actually use it, you're like, Holy smokes.

And I've been using it a non-technical tasks too.

And it's like, it is, you can see the reasoning just lower than like 5.4, but it, you know, it,

And I'm looking at the comments here.

It's like, for complex things that didn't do well.

Like, yeah, it was never designed to mimic 5.4 at the max.