reinforcement

DeepSeek R1’s bold bet on reinforcement learning: How it outpaced OpenAI at 3% of the cost

8 min read

DeepSeek R1’s bold bet on reinforcement learning: How it outpaced OpenAI at 3% of the cost

vi.sasori.vi January 26, 2025

Join our daily and weekly newsletters for the latest updates and exclusive content on...

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

4 min read

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

vi.sasori.vi January 20, 2025

Join our daily and weekly newsletters for the latest updates and exclusive content on...

New reinforcement learning method uses human cues to correct its mistakes

4 min read

New reinforcement learning method uses human cues to correct its mistakes

vi.sasori.vi December 5, 2023

Are you ready to bring more awareness to your brand? Consider becoming a sponsor...