How to Escape the Eval Cold Start Problem
Get your eval flywheel spinning as fast as safely possible.
Sunny's Blog
Hey there! I'm Sunny. I'm an AI optimist and obsessive builder. Currently, I'm a founding engineer at HoneyHive, where I'm building the dev tools and infrastructure to enable the next generation of AI agents.
Latest posts
Human Observability: The Final Bottleneck
Can working memory and attention help LLMs understand humans better?
Stop Writing Prompts Inside Your Code
A YAML-based configuration management tool for separating code from prompts in LLM applications.
How to Add Confidence Intervals to LLM Judges
Precision-Based Sampling for LLM Judges
AGI: A Reflection
A science fiction short story about the future of humanity and AGI.