reinforcement learning with verifiable rewards
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Nov 20, 2025 by Nathan Lambert · across every show →
Everything said about reinforcement learning with verifiable rewards, oldest first
Nov 20, 2025 neutral
Lambert: AI2 coined 'reinforcement learning with verifiable rewards' replicating Llama 3
“We spent a long time to try to replicate what we thought was close to Lama three post training with multiple stages and optimizers, which is the project that like came up with the name reinforcement learning with verifiable rewards with a bunch of people.”