Interconnects

Interconnects

Home
Podcast
Navigation
($) Discord
Archive
About

RLHF

Recent reasoning research: GRPO tweaks, base model RL, and data curation
The papers I endorse as worth reading among a cresting wave of reasoning research.
 • 
Nathan Lambert
2
Interviewing Eugene Vinitsky on self-play for self-driving and what else people do with RL
#13. Reinforcement learning fundamentals and scaling.
 • 
Nathan Lambert
1:09:22
Elicitation, the simplest way to understand post-training
An F1 analogy to help understand fast improvements in post-training on top of slow improvements in scaling.
 • 
Nathan Lambert
Character training: Understanding and crafting a language model's personality
Post-training in industry is very different than the academic papers and open-source models demonstrate. Let's dive into one of my favorite topics in…
 • 
Nathan Lambert
An unexpected RL Renaissance
New talk! Forecasting the Alpaca moment for reasoning models and why the new style of RL training is a far bigger deal than the emergence of RLHF.
 • 
Nathan Lambert
39:48
DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs
Yes, ring the true o1 replication bells for DeepSeek R1 🔔🔔🔔. Where we go next.
 • 
Nathan Lambert
2
The state of post-training in 2025
Watch now (54 mins) | A re-record of my NeurIPS tutorial on language modeling (plus some added content).
 • 
Nathan Lambert
53:50
OpenAI's o3: The grand finale of AI in 2024
A step change as influential as the release of GPT-4. Reasoning language models are the current big thing.
 • 
Nathan Lambert
4
OpenAI's Reinforcement Finetuning and RL for the masses
The cherry on Yann LeCun’s cake has finally been realized.
 • 
Nathan Lambert
Interviewing Finbarr Timbers on the "We are So Back" Era of Reinforcement Learning
Listen now | Interconnects interview #11. An overview on the past, present, and future of RL.
 • 
Nathan Lambert
 and 
Finbarr Timbers
1:08:32
OpenAI's o1 using "search" was a PSYOP
How to understand OpenAI's o1 models as really just one wacky, wonderful, long chain of thought
 • 
Nathan Lambert
2
Tülu 3: The next era in open post-training
We give you open-source, frontier-model post-training.
 • 
Nathan Lambert
3
© 2025 Interconnects AI, LLC
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture