DeepSeek-R1-Zero
4 statements across 1 episodes · 2 bullish · 0 bearish · 2 people on the record · first statement Mar 5, 2025 by Guido Appenzeller · said 17 times in 1 episodes since 2025 · across every show →
Mentions by year
brought up most by Marco Mascorro (12), Guido Appenzeller (5)
tap a year for its mentions
2025 17 mentions in 1 episode
Everything said about DeepSeek-R1-Zero, oldest first
Mar 5, 2025 positive
Mar 5, 2025 positive
Mar 5, 2025 neutral
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 …”
Mar 5, 2025 neutral
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…”