Re:Richard Sutton and Andrew Barto Win 2024 Turing Award
by perks_12 on Wednesday March 05, 2025 @07:54AM
(#43265850)
The Bitter Lesson seems to be generally accepted knowledge in the field. Wouldn't that make DeepSeek R1 even more of a breakthrough?
[ Parent
| on HN ]
Re:Richard Sutton and Andrew Barto Win 2024 Turing Award
by currymj on Wednesday March 05, 2025 @09:31AM
(#43266899)
that was “bitter lesson” in action.
for example there are clever ways of rewarding all the steps of a reasoning process to train a network to “think”. but deepseek found these don’t work as well as much simpler yes/no feedback on examples of reasoning.