Menu
Sign In Pricing Add Podcast

Lex Fridman Podcast

#459 – DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters

11327.645 - 11346.779 Dylan Patel

We use this in our like Tulu series of models and you can elicit the same behaviors where you say like weight and so much on, but it's so late in the training process that this kind of reasoning expression is much lighter. Yeah. So there's essentially a gradation, and just how much of this RL training you put into it determines how the output looks.

0
💬 0

Comments

There are no comments yet.

Log in to comment.