So one of my pet theories I haven't seen in general discourse is that AI came from the massive vector processing jump available commercially in GPUs when it left CPU bound processing behind. That's a factor of 100x-1000x of processing power.
AI is not-quite-there, and to get even another leap might take another 10-100x processing power.
Now... what? ASICs probably won't deliver even a 10x? There's only so much you get out of node shrinks.
"Substantial" doesn't even mean twice IMO. "Substantial" almost sounds like ... 15% better?
So one of my pet theories I haven't seen in general discourse is that AI came from the massive vector processing jump available commercially in GPUs when it left CPU bound processing behind. That's a factor of 100x-1000x of processing power.
AI is not-quite-there, and to get even another leap might take another 10-100x processing power.
Now... what? ASICs probably won't deliver even a 10x? There's only so much you get out of node shrinks.
"Substantial" doesn't even mean twice IMO. "Substantial" almost sounds like ... 15% better?