Comment by thomasahle
8 hours ago
• 98.6% on ARC-AGI-3
• 97.6% on frontier math
• 95.9% on CAD
• 100% on ExploitBench
Nothing modest about it
8 hours ago
• 98.6% on ARC-AGI-3
• 97.6% on frontier math
• 95.9% on CAD
• 100% on ExploitBench
Nothing modest about it
Except the release announcement. You know, the thing the OP you're responding to is specifically pointing out?
If a video announcement and a press release would change a person's mind on whether this is AGI, I don't put a huge amount of weight on that person's conception of what AGI is.