Caleb Biddulph comments on Why not train reasoning models with RLHF?

Caleb Biddulph 30 Jan 2025 16:53 UTC
1 point
0
Thanks! Apparently I should go read the r1 paper :)
- cubefox 30 Jan 2025 18:02 UTC
  2 points
  0
  Parent
  Actually the paper doesn’t have any more on this topic than the paragraph above.
  - Caleb Biddulph 30 Jan 2025 21:12 UTC
    1 point
    0
    Parent
    Yeah, but there are probably other interesting takeaways