AI compute shifts from custom ASICs to Google TPU and Nvidia
The speaker argued that most hyperscaler internal ASIC programs will fail over the next three years, consolidating the AI compute battle primarily between Google's TPU and Nvidia.
Sign in to read the full idea
The argument, what validates it, the risks discussed and hearing it from the source are for signed-in members. Free accounts read 3 ideas in full a day. No card required.