Skip to main content
Scour
Discover
Docs
Login
Sign Up
Discover
About
Docs
Changelog
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Deep (Learning) Focus
cameronrwolfe.substack.com
I contextualize and explain important topics in AI research.
cameronrwolfe.substack.com
·
4w
4 weeks ago
Agent Evaluation: A Detailed Guide
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Agent Evaluation: A Detailed Guide
cameronrwolfe.substack.com
·
8w
8 weeks ago
RL Scaling Laws for LLMs
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for RL Scaling Laws for LLMs
cameronrwolfe.substack.com
·
11w
11 weeks ago
The Anatomy of an LLM Benchmark
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The Anatomy of an LLM Benchmark
cameronrwolfe.substack.com
·
14w
14 weeks ago
Applying Statistics to LLM Evaluations
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Applying Statistics to LLM Evaluations
cameronrwolfe.substack.com
·
17w
17 weeks ago
Rubric-Based Rewards for RL
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Rubric-Based Rewards for RL
cameronrwolfe.substack.com
·
20w
20 weeks ago
Continual Learning with RL for LLMs
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Continual Learning with RL for LLMs
cameronrwolfe.substack.com
·
23w
23 weeks ago
GRPO++: Tricks for Making RL Actually Work
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for GRPO++: Tricks for Making RL Actually Work
cameronrwolfe.substack.com
·
26w
26 weeks ago
Olmo 3 and the Open LLM Renaissance
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Olmo 3 and the Open LLM Renaissance
cameronrwolfe.substack.com
·
29w
29 weeks ago
Group Relative Policy Optimization (GRPO)
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Group Relative Policy Optimization (GRPO)
cameronrwolfe.substack.com
·
33w
33 weeks ago
PPO for LLMs: A Guide for Normal People
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for PPO for LLMs: A Guide for Normal People
cameronrwolfe.substack.com
·
37w
37 weeks ago
REINFORCE: Easy Online RL for LLMs
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for REINFORCE: Easy Online RL for LLMs
cameronrwolfe.substack.com
·
40w
40 weeks ago
Online versus Offline RL for LLMs
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Online versus Offline RL for LLMs
cameronrwolfe.substack.com
·
43w
43 weeks ago
GPT-OSS from the Ground Up
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for GPT-OSS from the Ground Up
cameronrwolfe.substack.com
·
46w
46 weeks ago
Direct Preference Optimization (DPO)
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Direct Preference Optimization (DPO)
cameronrwolfe.substack.com
·
50w
50 weeks ago
Reward Models
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Reward Models
cameronrwolfe.substack.com
·
53w
53 weeks ago
AI Agents from First Principles
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for AI Agents from First Principles
cameronrwolfe.substack.com
·
56w
56 weeks ago
A Guide for Debugging LLM Training Data
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for A Guide for Debugging LLM Training Data
cameronrwolfe.substack.com
·
59w
59 weeks ago
Llama 4: The Challenges of Creating a Frontier-Level LLM
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Llama 4: The Challenges of Creating a Frontier-Level LLM
cameronrwolfe.substack.com
·
63w
63 weeks ago
Vision Large Language Models (VLLMs)
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Vision Large Language Models (VLLMs)
cameronrwolfe.substack.com
·
63w
63 weeks ago
NanoMoE: Mixture-of-Experts (Moe) LLMs from Scratch in PyTorch
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for NanoMoE: Mixture-of-Experts (Moe) LLMs from Scratch in PyTorch
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report