SentinelA new way to search

Search VoicesBlog

Sign In Sign Up

Sentinel keeps the record.

A permanent, searchable index of what is said in the video content shaping public conversation — built to support discovery and accountability across the voices that drive it.

Submit a Voice Request

Platform

Search
Browse Voices
Voices
Drive Again
Coverage
Custom Feed
Video Check
Statistics

Resources

Blog
Help
FAQ
Voice Request
Changelog
Sitemap

Company

About
Features
Pricing
Contact

Legal

Terms of Service
Privacy Policy
Acceptable Use
Cookies
Refund Policy
DMCA Policy

No content is hosted on Sentinel. All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel is an organization and analytics platform that provides research tools to promote discovery and accountability across the video content shaping public conversation. Views, credit, subscriptions, and engagement remain with the original channels.

© 2026 SentinelSearch. All rights reserved.

Indexing what Voices say, when they say it.

Nathan Lambert · Sentinel

Nathan Lambert

Nathan Lambert

@natolambert•8K subscribers•36 videos

Watch on YouTube Visit Website

About Nathan Lambert

Australian politician

Watch

YouTube Official Website Wikipedia

Listen

Apple Podcasts Spotify RSS Feed

Follow

Support

36

Videos

8K

Subscribers

100K

Total Views

Feb 3, 2021

Joined YouTube

Nathan Lambert Episode Catalog

Explore every episode. Find what matters.

The Mascot of Post-Training (Shoggoth History) | Post-training Course Bonus Video

177163

An Introduction to Character Training | Post Training Course, Lecture 13

1.3K665

How Evaluation Has Evolved with Frontier Model Progress | Post-Training Course, Lecture 12

1.3K664

Post-Training Recipe Questions Answered | Q&A 3, Post-Training Course (w/ The RLHF Book)

520266

How Language Models Use Tools and the Path to Agents | RLHF & Post-Training Course, Lecture 11

199126

From Academic Research to a Frontier LLM: A Case Study in DPO | RLHF Book Course, Conversation 2

1K346

Regularization in RL, Why RL Generalizes, and Why SFT Forgets | RLHF & Post-training Book Lecture 10

25194

Over-Optimization and RLHF’s Bad Reputation | Post-Training Course, Lecture 9

291214

Preference Data: The Most Opaque Part of Post-Training | RLHF & Post-training Course, Lecture 8

821445

Q&A 2: Mastering the Derivations, Running Algorithms at Home & Notation Gotcha's | RLHF Course

644221

ML Foundations (prerequisites) for Post-Training | RLHF Book Course, Lecture 0

1.8K11214

On-Policy Distillation & Using Synthetic Data in Post-Training | RLHF Book Course, Lecture 7

1.6K707

TMax: Open-Source Data for SOTA Terminal Agents

808512

The State of Frontier Post-Training Recipes | Conversation with Finbarr Timbers

100

Direct Preference Optimization (DPO) and Friends | RLHF & Post-training Course, Lecture 6

3200

The Rise of Reasoning Models | RLHF & Post-training Course Lecture 5

7530

Q&A 1: Teacher Models, PPO Implementation Questions & More | RLHF & Post-training Course

3620

Implementing RL Algorithms for LLMs | RLHF & Post-training Course, Lecture 4

2.4K7311

Understanding Policy Gradient Algorithms for RL on LLMs | RLHF & Post-training Course Lecture 3

2.9K11113

RLHF Foundations, IFT, Reward Modeling, Rejection Sampling | RLHF & Post-Training Course Lecture 2

3.3K999

RLHF and Post-training Overview | RLHF & Post-Training Book Course, Lecture 1

10.4K40423

Welcome to The RLHF Book & Post-Training Course

7.6K34314

A new RL Book is in town

1.9K283

Recapping Open Models in 2025

4.6K17612

Traits of next generation reasoning models

6.6K2388

Experimenting with Reinforcement Learning with Verifiable Rewards (RLVR)

13.4K4288

GRPO's new variants and implementation secrets

9.7K39412

Early stages of the reinforcement learning era of language models

5.4K1762

How to approach post-training for AI applications

6.6K2134

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

1.3K542

An update on DPO vs PPO for LLM alignment

4.1K1048

Open-source AI (and LLMs): Definitions, Finding Nuance, and Policy

740244

Introducing RewardBench: The First Benchmark for Reward Models (of the LLM Variety)

1.4K492

15min History of Reinforcement Learning and Human Feedback

4K1267

DPO Debate: Is RL needed for RLHF?

10.4K2768

[Unlisted Talk] Objective Mismatch in Reinforcement Learning from Human Feedback

5830

Reward Reports Brief Intro

10020

[Talk] Planning through Exploration and Exploitation in Model-based Reinforcement Learning

822270

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

33990

[Talk] Industry Review Talk: Machine Learning for Microsystem Control

10070

[Talk] Semiautonomous Seminar: Model learning for low-level control in robotics

11810

[Paper Summary] The Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

23740

[Talk] Cornell Robotics Seminar: MPC in MBRL

763220

[Talk] Bringing model-based RL to novel robotic platforms

20040

[Paper Summary] Objective Mismatch in Model-based Reinforcement Learning

29760

Showing 1–45 of 45

1/1