Reward Model

topic on 2 shows · 6 statements across 3 episodes

Latent Space Lenny's Podcast

6 statements about Reward Model, every show

Huyen: Comparative evaluation is significantly easier for humans than absolute scoring
“As humans we tend to, it's very hard to give, like, concrete score. But it's easier to do comparisons, right?”
Chip Huyen Oct 23, 2025 ▶ 16:44 Al Engineering 101 with Chip Huyen (Nvidia, Stanford, Netflix)
Reasoning models acting as reward models are key to agent RL
“And the most, one of the most promising ways, I think, towards doing this is having the reward models also be able to answer harder questions by themselves being reasoning models.”
Will Brown May 9, 2025 ▶ 11:54 ⚡️Open Questions in Agentic RL — Will Brown (Prime Intellect)
LATENT SPACE Assertion Not checkable as stated
Lambert: Real-Time Human Feedback in LLM RL Loops Is Far From Feasible
“Setting up the infrastructure to take tens of thousands of prompts and generate them and then show them to a human and collect the human responses and then show that Shove that into your training architecture is very far away from working, so we don't really h…”
Nathan Lambert Jan 11, 2024 ▶ 16:13 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
LATENT SPACE Assertion Supported
Lambert: Training LLM reward models on 0-to-10 ratings failed
“People tried that with language models, which is if you have a prompt and a completion and you just have someone rate it from zero to 10, could you then train a reward model on all of these completions and zero to 10 ratings and see if you could actually chang…”
Nathan Lambert Jan 11, 2024 ▶ 37:43 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
LATENT SPACE Assertion Supported
Lambert: RLHF reward models achieve only 65% to 75% validation agreement
“If you look at a test set, you'll have a chosen and rejected, and you can take the reward model you're training, pass in those completions, And you see if the chosen predicted reward, so the scalar number is higher than the rejected predicted reward, and this …”
Nathan Lambert Jan 11, 2024 ▶ 54:59 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
LATENT SPACE Assertion Supported
Lambert: OpenAI retrains reward models with curated and user prompt mixtures
“And this is like a sort of outer loop optimization that no one in the open is even remotely qualified to talk about, but OpenAI does monitor and they'll like rerun RLHF and train a new reward model with a mixture of their curated data and user prompts to try t…”
Nathan Lambert Jan 11, 2024 ▶ 1:32:27 The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show 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.