nathan lile (@nathanthinks) 's Twitter Profile
nathan lile

@nathanthinks

ceo/cofounder @ SynthLabs.ai hiring in SF 🌁

scaling synthetic reasoning.

recurrent rabbit hole victim.

nothing great is easy.

ID: 1709820956

calendar_today29-08-2013 11:46:27

1,1K Tweet

2,2K Takipçi

1,1K Takip Edilen

nathan lile (@nathanthinks) 's Twitter Profile Photo

What if models could learn which problems _deserve_ deep thinking? No labels. Just let the model discover difficulty through its own performance during training. Instead of burning compute 🔥💸 on trivial problems, it allocates 5x more on problems that actually need it ↓