Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
TuringsSolutions 
posted an update Oct 13
Post
523
Is Entropix the Chain of Thought Reasoning method behind GPTo1? Using a mixture of entropy, varentropy, and prompt engineering, the Entropix framework can straight up make SmolLLM 330M look like Llama 3.2. Check out this video for a full run down and the description of the video for all of the related resources you need: https://youtu.be/senq4_42tPI

i think o1 does use chain of thought

·

Reported, again. This person is literally pretending to be an AI researcher to stalk me. Click the links of their latest post, they are all blank. This person is straight up crazy. They post on all of my posts.

I am pretty sure that the actual models "AS THEY ARE" could perform 10 times better using chain of thought and some algorithms like these. Without needing a different training. And I think that's probably what CLAUDE does,