“As an industry we didn't optimize shit, pardon my French. I strongly believe that running inference, particularly with the variety of open-weight models that are available today, is not a solved problem. If you take something and just run with it as it's published, your results will probably be underwhelming. It's not that fast, it's not that cheap.”

…a way to do that. So in a sense, you don't need to fit anything in the rack. It's just, is there a workload that will benefit from this disbalance, like intentional disbalance of pre-fill and decode nodes? And can you fit more than one into a single rack? And how do you solve the packing problem?

Yeah, no, it makes sense. mentioned there's like lower hanging fruit on the uh on the inference side you know that than doing that maybe what what are like some of the lower hanging fruits today that you still think we're we're not uh as as as an industry optimized on

there's a ton of work around inference optimization and a lot of that gets done in open source right or like you know contributions that that share throughout the community there's obviously a bunch of work on on like smaller purpose-built models and and compaction and a bunch of these things…

we want to be at the forefront of everything in a sense these are additive and even maybe multiplicative right like if you have a right subset of things optimizations that you introduce for a particular use case it means that you can reach the targets easier better faster in a more predictable…

I guess, like, you know, maybe along those lines, you guys have done a few acquisitions, and one of them that caught a few people's eyes was Tavili in the kind of like web search space. Maybe talk through a little bit the rationale for that, how you think about that fitting into the broader…