Interconnects

Interconnects

Home
Podcast
Navigation
($) Discord
Archive
About

Reasoning & Inference Compute

The rise of reasoning machines
And a debate that doesn't warrant repeating.
 • 
Nathan Lambert
What comes next with reinforcement learning
Scaling RL, sparse rewards, continual learning, and the progress wall when pretraining really stops.
 • 
Nathan Lambert
2
A taxonomy for next-generation reasoning models
Where we've been and where we're going with RLVR.
 • 
Nathan Lambert
3
Reinforcement learning with random rewards actually works with Qwen 2.5
Making sense of research casting doubt on the potential of RLVR and where I'm optimistic for the next phase of scaling.
 • 
Nathan Lambert
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
© 2025 Interconnects AI, LLC
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture