Turn Eval Results Into a Better Model
In this video
What you'll learn
Build the right environment
Turn your system into an environment to evaluate and train models in
Know when to own a model
Decide when owning and training a model beats renting a closed one.
Close the loop with RL
Use reinforcement learning so the model gets better at your real tasks each round.
Why this topic matters
Environments are the foundation for evaluating and training models and agentic systems. They define the tasks, provide the context and tools, and determine how success is measured. Florian and Will from Prime Intellect will show you how to build effective environments, avoid common pitfalls, and use them to evaluate and train stronger models.
You'll learn from
Will Brown
Research Lead at Prime Intellect
Will Brown is Research Lead at Prime Intellect, where he builds open-source research and infrastructure for agentic reinforcement learning, including the verifiers library. He holds a PhD in algorithmic game theory from Columbia, co-advised by Christos Papadimitriou and Tim Roughgarden, and previously worked in Morgan Stanley's machine learning research group.
Florian Brand
Research Engineer at Prime Intellect
Florian Brand is a Research Engineer at Prime Intellect, where he works on LLM evals. He focuses on the practical side of evaluation: reproducibility, infrastructure, and building signals that models can actually improve on. He also writes and contributes to discussions on open models.
Hamel Husain
ML Engineer with 20+ years of experience
Hamel Husain is a ML Engineer with 20+ years of experience. He has worked with companies such as Airbnb and GitHub, which included early LLM research used by OpenAI, for code understanding. He has also led and contributed to numerous popular open-source machine-learning tools. Hamel is currently an independent developer helping companies with applied evals.
Go deeper with a course
Featured in Lenny’s List
AI Evals For Engineers & PMs
Hamel Husain and Shreya Shankar
ML Engineer with 20+ years of experience.. ML Systems Researcher Making AI Evaluation Work in Practice
Keep exploring
