Ai Benchmarks

Ai Benchmarks

A crowd of people wearing sunglasses looks upward; Brendan Foody is featured on the left side of the image, where a rising line graph appears on a dark background.
AI “eval” outfit Mercor is one of the fastest growing companies in history. But will their rocket run out of fuel? Big Think investigates.
Image of a tomato and carrot, each partially overlaid with a black and white digital circuit pattern. The background is a gray, circuit-like texture.
A simple plate of vegetables has found the gaping blindspots in generative AI, and points the way to fixing them.