# @davidad — 2025-05-01

♥15 ↻0 · https://x.com/davidad/status/1917747744673874099

@ChrisChipMonk (Self-Correction:) The earlier DeepSeek v3 and even prior generations of DeepSeek LLMs had a similar hybrid-MoE arch. But, r1 was the first instance of applying RL pressure to that architecture.

tags: author:davidad, kind:tweet, model:deepseek-r1, model:deepseek-v3, on:deepseek-v3, year:2025
cited on: _dossiers/deepseek-v3.md, deepseek-v3
