Holy smokes! The DeepSeek-R1 team just published the path to superintelligence! “…instead of forcing the model to copy human reasoning steps, it only rewards getting the final answer right, which gives the model freedom to invent its own reasoning strategies that can actually https://t.co/W1AFyBgLAH
— Derya Unutmaz, MD (@DeryaTR_) Sep 18, 2025
from Twitter https://twitter.com/DeryaTR_
September 18, 2025 at 10:55AM
via IFTTT
No comments:
Post a Comment