Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on 44% on ARC-AGI-1 in 67 cents. Parent comment
Yepp
> Also aren't frontier models trained 'from scratch'?
The full sentence was supposed to be "training from scratch only on ARC data"
the point was you dont need large scale pretraining
There are no comments on this comment yet.
Yepp
> Also aren't frontier models trained 'from scratch'?
The full sentence was supposed to be "training from scratch only on ARC data"
the point was you dont need large scale pretraining