Interconnects

Interconnects

Home
Podcast
Navigation
($) Discord
Archive
About

Reasoning & Inference Compute

OpenAI's o3: Over-optimization is back and weirder than ever
Tools, true rewards, and a new direction for language models.
 • 
Nathan Lambert
RL backlog: OpenAI's many RLs, clarifying distillation, and latent reasoning
Notes I forgot to publish. Closing some loose ends in the reasoning model discussions.
 • 
Nathan Lambert
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
Gemini 2.5 Pro and Google's second chance with AI
The end of a busy spring of model improvements and what's next for the presumed leader in AI abilities.
 • 
Nathan Lambert
Where inference-time scaling pushes the market for AI companies
Fundamentals emerging downstream from the RL reasoning models.
 • 
Nathan Lambert
1
Claude 3.7 thonks and what's next for inference-time scaling
The latest reasoning model and what it says about the direction of inference time compute and RL training.
 • 
Nathan Lambert
1
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
Why reasoning models will generalize
People underestimate the long-term potential of “reasoning.”
 • 
Nathan Lambert
7
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
Quick recap on the state of reasoning
My talk at the NeurIPS Latent Space live event.
 • 
Nathan Lambert
1
16:21
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 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
© 2025 Interconnects AI, LLC
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture