Podcast · 156 episodes on record

(Voiceover) Tülu 3: The next era in open post-training

Published

November 21, 2024

Length

7 min

Position

63 of 156

November 21, 2024

(Voiceover) Tülu 3: The next era in open post-training

0:00 / 7:59

0:00Choose a match or chapter to light up its moment7:59

Listen to the full episode

Excerpt playback isn’t available for this episode — use the full-episode link.

Search the Record

Moment search isn’t open for this episode yet

When it opens, you’ll be able to type any phrase and jump straight to the second it was said.

Nathan Lambert Episodes Around November 21, 2024

Episode 63 of 156 — walk the feed in the order it was published.

View all episodes

11:31

Futures of the data foundry business model

Sep 11, 2024

18:51

[Article Voiceover] Reverse engineering OpenAI's o1

Sep 17, 2024

14:04

[Article Voiceover] Llama 3.2 Vision and Molmo: Foundations for the multimodal open-source ecosystem

Sep 27, 2024

1:08:39

Interviewing Andrew Trask on how language models should store (and access) information

Oct 10, 2024

16:36

(Voiceover) Building on evaluation quicksand

Oct 16, 2024

54:21

Interviewing Arvind Narayanan on making sense of AI hype

Oct 17, 2024

11:23

(Voiceover) Claude's agentic future and the current state of the frontier models

Oct 23, 2024

10:19

(Voiceover) Why I build open language models

Oct 30, 2024

54:10

Interviewing Andrew Carr of Cartwheel on the State of Generative AI

Oct 31, 2024

1:15:45

Interviewing Tim Dettmers on open-source AI: Agents, scaling, quantization and what's next

Nov 7, 2024

11:22

(Voiceover) Saving the National AI Research Resource & my AI policy outlook

Nov 13, 2024

4:21

(Voiceover) Scaling realities

Nov 14, 2024

7:59This episode

(Voiceover) Tülu 3: The next era in open post-training

Nov 21, 2024

10:26

(Voiceover) OLMo 2 and building effective teams for training language models

Nov 26, 2024

12:13

(Voiceover) OpenAI's o1 using "search" was a PSYOP

Dec 4, 2024

1:08:33

Interviewing Finbarr Timbers on the "We are So Back" Era of Reinforcement Learning

Dec 5, 2024

12:40

(Voiceover) OpenAI's Reinforcement Finetuning and RL for the masses

Dec 11, 2024

11:00

(Voiceover) The AI agent spectrum

Dec 18, 2024

17:58

(Voiceover) OpenAI's o3: The grand finale of AI in 2024

Dec 20, 2024

6:02

(Voiceover) 2024 Interconnects year in review

Dec 31, 2024

16:22

Quick recap on the state of reasoning

Jan 2, 2025

53:50

The state of post-training in 2025

Jan 8, 2025

17:06

(Voiceover) DeepSeek V3 and the actual cost of training frontier AI models

Jan 9, 2025

10:21

Let me use my local LMs on Meta Ray-Bans

Jan 15, 2025

19:33

DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs

Jan 21, 2025

1:12:43

Interviewing OLMo 2 leads: Open secrets of training language models

Jan 22, 2025

11:37

Why reasoning models will generalize

Jan 28, 2025

16:13

Making the U.S. the home for open-source AI

Feb 5, 2025

View all episodes

Summary

Original post: <a href="https://www.interconnects.ai/p/tulu-3" target="_blank">https://www.interconnects.ai/p/tulu-3</a>Chapters00:00 History05:44 Technical details sneak peakFiguresFig 1, results: <a href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/results.webp" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/results.webp</a>Fig 2, overview: <a href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/overview.webp" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/overview.webp</a>Fig 3, preferences: <a href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/preferences.webp" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/preferences.webp</a>Fig 4, RLVR: <a href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/rlvr.webp" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/tulu3-img/rlvr.webp</a> This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit <a href="https://www.interconnects.ai/subscribe?utm_medium=podcast&utm_campaign=CTA_2">www.interconnects.ai/subscribe</a>

Episode details and artwork are published by the show’s own feed. Sentinel plays short cited excerpts and links every episode back to its publisher.

← All episodes from Nathan Lambert

(Voiceover) Tülu 3: The next era in open post-training

Search the Record

Nathan Lambert Episodes Around November 21, 2024

Futures of the data foundry business model

[Article Voiceover] Reverse engineering OpenAI's o1

[Article Voiceover] Llama 3.2 Vision and Molmo: Foundations for the multimodal open-source ecosystem

Interviewing Riley Goodside on the science of prompting

[Article Voiceover] AI Safety's Crux: Culture vs. Capitalism

How scaling changes model behavior

Interviewing Andrew Trask on how language models should store (and access) information

(Voiceover) Building on evaluation quicksand

Interviewing Arvind Narayanan on making sense of AI hype

(Voiceover) Claude's agentic future and the current state of the frontier models

(Voiceover) Why I build open language models

Interviewing Andrew Carr of Cartwheel on the State of Generative AI

Interviewing Tim Dettmers on open-source AI: Agents, scaling, quantization and what's next

(Voiceover) Saving the National AI Research Resource & my AI policy outlook

(Voiceover) Scaling realities

(Voiceover) Tülu 3: The next era in open post-training

(Voiceover) OLMo 2 and building effective teams for training language models

(Voiceover) OpenAI's o1 using "search" was a PSYOP

Interviewing Finbarr Timbers on the "We are So Back" Era of Reinforcement Learning

(Voiceover) OpenAI's Reinforcement Finetuning and RL for the masses

(Voiceover) The AI agent spectrum

(Voiceover) OpenAI's o3: The grand finale of AI in 2024

(Voiceover) 2024 Interconnects year in review

Quick recap on the state of reasoning

The state of post-training in 2025

(Voiceover) DeepSeek V3 and the actual cost of training frontier AI models

Let me use my local LMs on Meta Ray-Bans

DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs

Interviewing OLMo 2 leads: Open secrets of training language models

Why reasoning models will generalize

Making the U.S. the home for open-source AI

Summary