RLHF

4 statements across 3 episodes · 3 bullish · 0 bearish · 3 people on the record · first statement Feb 28, 2023 by Raza Habib · across every show →

Everything said about RLHF, oldest first

Feb 28, 2023 positive
Assertion Supported
Habib: Anthropic matched RLHF performance using AI-generated feedback
“Anthropic had this very exciting paper just a couple of weeks ago where actually we're able to get similar results to RLHF without the H. So just actually having a second model provide the evaluation feedback as well. And that's obviously a lot more scalable.”
Raza Habib Feb 28, 2023 ▶ 6:07 The REAL potential of generative AI · Y Combinator
May 30, 2025 positive
Insight
Diana Hu: XML Prompts Produce Better Output Due to Post-Training RLHF
“We found that it makes it a lot easier for LLMs to follow, because a lot of elements were post-trained in RLHF with kind of XML type of input, and it turns out to produce better results.”
Diana Hu May 30, 2025 ▶ 3:43 State-Of-The-Art Prompting For AI Agents · Y Combinator
May 30, 2025 neutral
Opinion
Hu: Claude is naturally human-steerable while Llama requires heavy prompting
“One of the things that's known a lot is Claude is sort of the more happy and more human steerable model, and the other one is Lama. Four is one that needs a lot more steering. It's almost like talking to a developer, and part of it could be an artifact of not …”
Diana Hu May 30, 2025 ▶ 26:28 State-Of-The-Art Prompting For AI Agents · Y Combinator
Apr 29, 2026 bullish
Prediction Not checkable as stated
Hassabis: Current AI paradigms will be part of final AGI architecture
“The components that you just mentioned, I'm pretty sure will be part of the final architecture for AGI. So I think they've come such a long way now and we've proven out so many things about what they can do. I can't see a world in which we will sort of realize…”
Demis Hassabis Apr 29, 2026 ▶ 2:22 Demis Hassabis: Agents, AGI & The Next Big Scientific Breakthrough · Y Combinator
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 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.