Comment on Announcing ARC-AGI-3 - An benchmark that tests if AI can explore, learn, and adapt in unfamiliar situations. Humans score 100%. Frontier AI scores 0.26%.

HaunchesTV@feddit.uk ⁨1⁩ ⁨week⁩ ago

Grok Reasoning: 0%

Hilarious

source
Sort:hotnewtop