Subscribe
Sign in
Home
Podcast
($) Discord
Read SAIL
Archive
About
Reasoning & Inference Compute
Latest
Top
Discussions
New Talk: Building Olmo 3 Think
Re-recording my NeurIPS talks in one mega-take.
Dec 10
•
Nathan Lambert
50
5
6
1:02:21
How to scale RL
The most covetable research.
Oct 20
•
Nathan Lambert
83
3
8
Thinking, Searching, and Acting
A reflection on reasoning models.
Sep 22
•
Nathan Lambert
90
17
5
Crafting a good (reasoning) model
A recent talk I gave on model training, reasoning, and the next frontier.
Jun 18
•
Nathan Lambert
55
6
30:25
The rise of reasoning machines
And a debate that doesn't warrant repeating.
Jun 12
•
Nathan Lambert
79
13
What comes next with reinforcement learning
Scaling RL, sparse rewards, continual learning, and the progress wall when pretraining really stops.
Jun 9
•
Nathan Lambert
74
2
15
A taxonomy for next-generation reasoning models
Where we've been and where we're going with RLVR.
Jun 4
•
Nathan Lambert
66
3
15
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.
May 27
•
Nathan Lambert
86
17
OpenAI's o3: Over-optimization is back and weirder than ever
Tools, true rewards, and a new direction for language models.
Apr 19
•
Nathan Lambert
126
9
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.
Apr 5
•
Nathan Lambert
52
10
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.
Mar 31
•
Nathan Lambert
79
2
17
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.
Mar 26
•
Nathan Lambert
75
11
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
