StarZero All shows Try the podcast clipper →

rejection sampling

2 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Jan 11, 2024 by Nathan Lambert · across every show →

Everything said about rejection sampling, oldest first

Jan 11, 2024 positive
Assertion Supported
Lambert: Meta Used Rejection Sampling to Bootstrapping Llama 2 RLHF
“Llama started their RLHF process with this to get some signal out of preference data. That preference data went into a reward model, and then the reward model did a good enough ranking that it was, like, essentially superpowered instruction tuning based on rew…”
Nathan Lambert Jan 11, 2024 ▶ 1:03:01 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
Jan 26, 2025
Disclosure
Beauchamp: Chai avoids response streaming to enable UI rejection sampling
“Chai has never done streaming. Because if you stream, you're unable to do rejection sampling.”
William Beauchamp Jan 26, 2025 ▶ 1:08:52 Outlasting Noam Shazeer, Crowdsourcing Chai AI w/ 1.4m DAU — with William Beauchamp, Chai Research
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