Ken Mueller

Sup AI

CEO at Sup AI · Stanford

#553310223 followers 1 following

About

No single AI model is right all the time, and their errors don't strongly correlate. So I built Sup AI: a confidence-weighted ensemble that synthesizes multiple LLMs into one better answer. My dad Scott (AI Research Scientist, TRI/UCLA) is my research partner. Stanford CS.

Badges

Tastemaker

Gone streaking

Maker History

Sup AIAI ensemble that scored #1 on Humanity's Last Exam
Apr 2026

🎉

Joined Product HuntMay 10th, 2023

Forums

•

1mo ago

Sup AI - AI ensemble that scored #1 on Humanity's Last Exam

Every LLM hallucinates. They just don't hallucinate the same things. Sup AI runs multiple LLMs (out of 339) in parallel, then synthesizes answers by measuring confidence on every segment. High entropy = likely hallucination, downweighted. Low entropy = likely accurate, amplified. Result: 52.15% on Humanity's Last Exam, 7.41 points ahead of any individual model. $10 starter credit. Card verified. No auto-charge.