DeepSeek R1 Zero
product on 3 shows · 4 statements across 1 episodes · said 24 times in 7 episodes since 2025
the a16z Podcast 17 
Latent Space 5 
TBPN 2
Mentions by year, every show
tap a year for its mentions
the a16z Podcast 17Latent Space 5TBPN 2
2026 1 mention in 1 episode
2025 23 mentions in 6 episodes 4 per episode
- DeepSeek, Reasoning Models, and the Future of LLMs
- DeepSeek Update, Market Crash, Timeline in Turmoil, Is VC Cooked, Zero Cope Policy
- [State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor
- What is an RL environment? w/ Nous Research's Roger Jin
- S1: the $6 DeepSeek R1 Competitor (ft. Entropix)
- The Unreasonable Effectiveness of Reasoning Distillation: using DeepSeek R1 to beat OpenAI o1
- every mention in 2025, scene by scene →
every mention on every show, scene by scene, with the transcript →
4 statements about DeepSeek R1 Zero, every show
Mascorro: DeepSeek-R1-Zero Improved Math Scores but Struggled with Readability and Language Switching
“R one zero, which in a way was a very interesting model because it showed that it improved in some reasoning benchmarks and math benchmarks. But eventually didn't do really well on other things, right? Like it was switching between languages. I think that was …”
Appenzeller: DeepSeek-R1-Zero is arguably better at reasoning than the final R1
“DeepSeq R-one-zero is actually a very, very good reasoning model. It's arguably better in reasoning than the final DeepSeq R-one.”
Mascorro: DeepSeek-R1 post-training used two SFT and two RL phases
“So basically the way they did that, trying to fix R one zero, is it added a couple more phases in the post-training. That included two supervised fine tuning phases and two reinforcement learning phases. And these reinforcement learning phases, they were a lar…”