Remix.run Logo
fooker an hour ago

We don't really train deployed models in realtime in any realistic sense nowadays.

It used to be a thing when ML was pretty much about classifying things into buckets.

LogicFailsMe an hour ago | parent | next [-]

May I introduce you to the word of our lord the arc-agi-3 kaggle competition?

Because that's how they've hit 18% on a single RTX Pro 6000 with DIY RSI.

fooker 39 minutes ago | parent [-]

Where can I read more about this?

LogicFailsMe 17 minutes ago | parent [-]

https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-3

bigfishrunning an hour ago | parent | prev [-]

> ML was pretty much about classifying things into buckets.

It still is, it's just that there are a ton of buckets.