Product Evals in Three Simple Steps
After repeating myself for the $n^text{th}$ time on how to build product evals, I figured I should write it down.…
2025 Year in Review
2025 was an eventful year of progress. I doubled down on my health, had some pleasant career surprises, and my…
How to Work and Compound with AI
How can we work effectively with AI? What’s the workflow, how does it scale, and how do we improve our…
Using LLMs to Secure Source Code
Build a threat model, discover vulnerabilities, verify, triage, and patch.
Patterns for Building Cybersecurity Evals
How do we evaluate if a model can find and exploit security vulnerabilities? How do we know when agents become…
Extrinsic Hallucinations in LLMs
Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term,…
Reward Hacking in Reinforcement Learning
Reward hacking occurs when a reinforcement learning (RL) agent exploits flaws or ambiguities in the reward function to achieve high…
Why We Think
Special thanks to John Schulman for a lot of super valuable feedback and direct edits on this post.
Scaling Laws, Carefully
Scaling laws are one of the most critical empirical findings in deep learning. The observation is simple in form: the…
Harness Engineering for Self-Improvement
The concept of recursive self-improvement (RSI) dates back to I. J. Good (1965), where he defined an “ultraintelligent machine” as…