The host asked whether Google goes back and swaps out the chips in older data centers, and how long an AI chip really stays useful. Vahdat repeated a remark he said had drawn more attention than he expected when he first made it. TPUs are Google's own AI accelerator chips.
…But now we wind up having individual model endpoints, and there actually can be variations of models. So now we have to spread these models out across the world, also accounting for locality. So they will be smaller. They'll actually be less vertically integrated, probably, on the inference side.
…ago was very different, vastly less efficient than the ones that are being made today. Yes. Do you actually go back and like swap out the chips in those old data centers? And I know this kind of relates to there's been an ongoing debate, I think, of like what is the actual useful life of a chip.
Yeah. Yeah. So, you know, I've been on record of saying this in one of my more, I was surprised by how much pickup this had. But, you know, I said that our seven and eight-year-old TPUs are still at 100% utilization.
Wow.
I think I saw
this. I didn't realize this from the case. Yeah,