Re:DeepSeek-R1
by wrsh07 on Monday January 20, 2025 @09:48PM
(#42775894)
Given how it is trained specifically (they didn't encourage it to think, they allowed it to) there was a lot of emergent behavior as it trained.
Sort of like chess engines rediscovering classic (named) chess openings. See section 2.2.3 for the training template (it's a single paragraph I can't reproduce here because I'm on my phone)
Example emergent behavior (section 2.2.4 page 8): the model learns to solve more complex problems by spending more time reasoning. It also naturally develops reflection (what have I tried?) and exploration strategies.
Fundamentally, you should think of this as a nn that learned to solve real problems by reasoning about them in written language.
(My favorite part: it defaulted to reasoning in multiple languages. They constrained it to only reason in a single language and this negatively impacted performance! But the hypothesis is that it improves interpretability)
Sort of like chess engines rediscovering classic (named) chess openings. See section 2.2.3 for the training template (it's a single paragraph I can't reproduce here because I'm on my phone)
Example emergent behavior (section 2.2.4 page 8): the model learns to solve more complex problems by spending more time reasoning. It also naturally develops reflection (what have I tried?) and exploration strategies.
Fundamentally, you should think of this as a nn that learned to solve real problems by reasoning about them in written language.
(My favorite part: it defaulted to reasoning in multiple languages. They constrained it to only reason in a single language and this negatively impacted performance! But the hypothesis is that it improves interpretability)