Deep (Learning) Focus

The Anatomy of an LLM Benchmark

Common patterns used to create the most effective LLM evaluation datasets...

Mar 30 • Cameron R. Wolfe, Ph.D.

96

2

15

Applying Statistics to LLM Evaluations

Most LLM evaluations are conducted without a deep consideration of statistics.

Mar 9 • Cameron R. Wolfe, Ph.D.

126

8

13

February 2026

Rubric-Based Rewards for RL

Extending the benefits of large-scale RL training to non-verifiable domains...

Feb 16

117

9

17

January 2026

Continual Learning with RL for LLMs

Exploring the impressive continual learning capabilities of RL training...

Jan 26 • Cameron R. Wolfe, Ph.D.

145

15

19

GRPO++: Tricks for Making RL Actually Work

How to go from the vanilla GRPO algorithm to functional RL training at scale...

Jan 5 • Cameron R. Wolfe, Ph.D.

130

10

18

December 2025

Olmo 3 and the Open LLM Renaissance

Fully-open artifacts with the potential to make LLM research a reality for anyone...

Dec 15, 2025 • Cameron R. Wolfe, Ph.D.

82

7

14

November 2025

Group Relative Policy Optimization (GRPO)

How the algorithm that teaches LLMs to reason actually works...

Nov 24, 2025 • Cameron R. Wolfe, Ph.D.

114

10

14

October 2025

PPO for LLMs: A Guide for Normal People

Understanding the complex RL algorithm that gave us modern LLMs…

Oct 27, 2025 • Cameron R. Wolfe, Ph.D.

168

11

14

September 2025

REINFORCE: Easy Online RL for LLMs

How to get the benefits of online RL without the complexity of PPO...

Sep 29, 2025 • Cameron R. Wolfe, Ph.D.

100

11

6

Online versus Offline RL for LLMs

A deep dive into the online-offline performance gap in LLM alignment...

Sep 8, 2025 • Cameron R. Wolfe, Ph.D.

89

4

10

August 2025

GPT-oss from the Ground Up

Everything you should know about OpenAI's new open-weight language models...

Aug 18, 2025 • Cameron R. Wolfe, Ph.D.

102

14

15

July 2025

Direct Preference Optimization (DPO)

How to align LLMs with limited hardware and minimal complexity...

Jul 28, 2025 • Cameron R. Wolfe, Ph.D.

128

20

11