GRPO
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Apr 25, 2025 by Aravind Srinivas · across every show →
Everything said about GRPO, oldest first
Apr 25, 2025 bullish
Srinivas: Perplexity plans to invest more in RL post-training this year
“The nice thing is a lot of open source code bases exist on how to replicate GRPO or PPO and post training these models. And we've been doing that work already. So that's where we plan to invest more resources into for this year.”