• Thu. Feb 13th, 2025

Open-source DeepSeek-R1 uses pure reinforcement learning to match OpenAI o1 — at 95% less cost

By

Jan 20, 2025

The company developed DeepSeek-R1 by using pure reinforcement learning on top of DeepSeek-V3-Base, and matched or beat o1 on some benchmarks.Read More

Leave a Reply

Your email address will not be published. Required fields are marked *

Generated by Feedzy