logoalt Hacker News

SwellJoetoday at 9:18 AM1 replyview on HN

The models have to run on something or they're useless. They can't run on future hardware today, and people want to use models today. So, if hardware is obsolete the day it ships, we're all using obsolete hardware, and there's no alternative to that.


Replies

otterleytoday at 12:20 PM

Taalas encodes the model into the hardware itself. The two are inextricably coupled. It’s like buying a CNC router that can’t be reprogrammed to build anything other than a specific predetermined kitchen cabinet. And the model used inside is frozen many months before the hardware ships, since the process from tapeout to production takes that long.

In contrast, tomorrow’s models will typically run, although perhaps more slowly, on general-purpose inference hardware that was released today or even years ago.