Everything You Wanted to Know About LLM Post-Training, with Nathan Lambert of Allen Institute for AI

(1:49:41)

Nathan Lambert - Reinforcement Learning from Human Feedback @ UCL DARK

(47:16)

How to approach post-training for AI applications

(22:4)

Stanford CS25: V4 I Aligning Open Language Models

(1:16:21)

DeepSeek, China, OpenAI, NVIDIA, xAI, TSMC, Stargate, and AI Megaclusters | Lex Fridman Podcast #459

(5:6:19)

Tulu 3: Exploring Frontiers in Open Language Model Post-Training - Nathan Lambert (AI2)

(1:1:45)

Nathan Lambert - The Truth About DeepSeek AI

(21:14)

The State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]

(16:22)

791: Reinforcement Learning from Human Feedback (RLHF) — with Dr. Nathan Lambert

(55:54)

15min History of Reinforcement Learning and Human Feedback

(17:24)

Nathan Lambert of New Rules Loves His Omelettes

(2:9)

Nathan Lambert of New Rules is a Bad Cook!?

(2:1econd)

Nathan Lambert and Dylan Patel - Why DeepSeek AI Is So Cheap

(11:)

[Talk] Dissertation Talk: Synergy of Prediction and Control in Model-based Reinforcement Learning

(36:23)

Deep Dive into LLMs like ChatGPT

(3:31:24)

Building LLMs from the Ground Up: A 3-hour Coding Workshop

(2:45:10)

Girl Geek X @OpenAI Lightning Talks \u0026 Panel

(1:46:35)

Honeypot sex espionage explained | Dylan Patel and Nathan Lambert and Lex Fridman

(1:54)

Self-directed Synthetic Dialogues (and other recent synth data)

(15:51)

Elon Musk's massive xAI data center in Memphis | Dylan Patel and Nathan Lambert and Lex Fridman

(13:23)

PACIFIC RIM UPRISING Cast Interview Soundbite: Scott Eastwood - \

(1:30)