News for hackers. Stuff that matters.
Re:ARC-AGI without pretraining by ta8645 on Tuesday March 04, 2025 @04:00PM (#43259753)
Yes, but that just effectively recreates the pretraining. You're going to have to explain everything down to what an atom is, and essentially all human knowledge if you want to have any ability to consider abstract solutions that call on lessons from foreign domains.

There's a reason people with comparable intelligence operate at varying degrees of effectiveness, and it has to do with how knowledgeable they are.

Re:ARC-AGI without pretraining by pona-a on Tuesday March 04, 2025 @04:39PM (#43260067)
Would that make in-context learning a superset or a subset of pretraining?

This paper claimed transformers learn a gradient-descent mesa-optimizer as part of in-context learning, while being guided by the pretraining objective, and as the parent mentioned, any general reasoner can bootstrap a world model from first principles.

[0] https://arxiv.org/pdf/2212.07677

Re:ARC-AGI without pretraining by ta8645 on Tuesday March 04, 2025 @05:00PM (#43260260)
> Would that make in-context learning a superset or a subset of pretraining?

I guess a superset. But it doesn't really matter either way. Ultimately, there's no useful distinction between pretraining and in-context learning. They're just an artifact of the current technology.