[fchollet]

It is correct that the first model that will beat ARC-AGI will only be able to handle ARC-AGI tasks. However, the idea is that the architecture of that model should be able to be repurposed to arbitrary problems. That is what makes ARC-AGI a good compass towards AGI (unlike chess).

For instance, current top models use TTT, which is a completely general-purpose technique that provides the most significant boost to DL model's generalization power in recent memory.

The other category of approach that is working well is program synthesis -- if pushed to the extent that it could solve ARC-AGI, the same system could be redeployed to solve arbitrary programming tasks, as well as tasks isomorphic to programming (such as theorem proving).

[ipunchghosts]

"However, the idea is that the architecture of that model should be able to be repurposed to arbitrary problems"

From a mathematical perspective, this doesn't sound right. All NNs are universal apprxomators and in theory can all learn the same thing to equal ability. It's more about the learning algorithm than the architecture IMO.

[scoobertdoobert]

François, have you coded and tested a solution yourself that you think will work best?

[optimalsolver]

Hey, he's the visionary. You come up with the nuts and bolts.

[homarp]

is keras nuts and bolts enough?

[ipunchghosts]

Keres is a good abstraction model but poorly implemented.