minus-squareAceticon@lemmy.dbzer0.comtoTechnology@lemmy.world•Announcing ARC-AGI-3 - A benchmark that tests if AI can explore, learn, and adapt in unfamiliar situations. Humans score 100%. Frontier AI scores 0.26%.linkfedilinkEnglisharrow-up1·2 days agoAs a random person on the Internet I don’t actually have anything to add but felt it would be nice to jump in. linkfedilink
As a random person on the Internet I don’t actually have anything to add but felt it would be nice to jump in.