Ivan rambles on about LLM reliability, evals and UX design
Engineer, Writer and Amateur designer
Currently engineering at 567 labs
ABOUT ME
Ivan Leo
Hailing from the sunny island of Singapore, I'm a Research Engineer passionate about Language Models. I maintain open source libraries like Instructor (3M+ downloads) and actively contribute to projects like Kura.
I've had the privilege of working with clients like Hubspot and Raycast, and recently worked on a RAG course taken by engineers from OpenAI, Anthropic, DeepMind, and Bain.
I'm also a big fan of the outdoors, and love to go hiking, biking, and swimming. When I'm not working, you can find me exploring the great outdoors or Singapore's fantastic food scene.
RECENT THOUGHTS
Ideas worth sharing,
all in one place
Write Stupid Evals
Start simple with evals and build up complexity gradually. The best evaluation isn't the most sophisticated one - it's the one you'll actually use consistently.
read more→
Synthetic Data is not a Free Lunch
Hard-earned lessons from generating millions of synthetic data points and why validation matters more than volume. Success requires careful thought and systematic validation.
read more→
You're probably not doing experiments right
Three key factors that make the biggest difference in LLM experiments: being clear about what you're varying, investing in infrastructure, and doing sensitivity analysis.
read more→