|
|
|
|
|
|
by OrvalWintermute
58 days ago
|
|
|
I think the company Taalas alone destroys Ed’s arguments Because, comparing vs GPUs ~16k–17k tokens/second per user <1ms latency 10x power efficiency 20x cheaper production Model to Si ~ 60 to 90 days We have every reason to believe SW_to_Si will facilitate improving economics |
|
|