RL techniques
1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement May 1, 2026 by Tuhin Srivastava · across every show →
Everything said about RL techniques, oldest first
May 1, 2026 bullish
Srivastava: Open-Source Baseline and Post-Training Enable In-House Inference
“The open source models have crossed some sort of chasm in terms of their baseline. Capability, and then I think RL techniques and post-training is for specialized models has become mainstream enough, and, you know, there's enough examples of its work, of it wo…”