StarZero All shows Try the podcast clipper →

verifiable rewards

2 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Jul 31, 2025 by Nathan Lambert · across every show →

Everything said about verifiable rewards, oldest first

Jul 31, 2025 positive
Insight
Lambert: RLVR is broader than ground truth because code is verifiable
“The verifiable rewards is actually a more general notion because only like math questions have a ground truth where code is verifiable, precise instruction following is verifiable.”
Nathan Lambert Jul 31, 2025 ▶ 5:13 The RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)
Jan 28, 2026
Insight
White: Writing bulletproof RL verifiers is far harder than supervised training
“Pre-training or training transformers, you know on just data, like just supervised training where you just have the inputs and the outputs directly, very nice, relaxing, you know, like things are always robust, you know, things go pretty smoothly. When we do t…”
Andrew White Jan 28, 2026 ▶ 1:12:03 🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew White
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more