Comment by modeless
7 months ago
Interesting that this wasn't tested on ARC-AGI. Francois has always said he believed program search of this type was the key to solving it. It seems like potentially this approach could do very well.
7 months ago
Interesting that this wasn't tested on ARC-AGI. Francois has always said he believed program search of this type was the key to solving it. It seems like potentially this approach could do very well.
My thought as well. How well does it translate into arc agi? If it does well then we have a general purpose super intelligence… so maybe agi?
Given they didn't report how good it is at it, it's probably not very good at it.