Pretty cool. Shameless plug: My team at Anthropic is hiring people that can write accelerator kernels. Please reach out to <my username>@gmail.com if you want to make state of the art models faster :)
It's funny - former Google devs (whom I just maintain a good relationship with their former employer) are ideally positioned to profitably take advantage of the arb of TPU over GPU.
Google should improve their abstractions until there isn’t room for that anymore, haha.