I don't know what he could mean by that, as the whole idea behind ARC-AGI is to "target the benchmark." Got any links that explain further?
The fact that ARC-AGI has public and semi-private in addition to private datasets might explain it: https://arcprize.org/arc-agi/2/#dataset-structure
The fact that ARC-AGI has public and semi-private in addition to private datasets might explain it: https://arcprize.org/arc-agi/2/#dataset-structure