In the depths of winter the activity at the top of our lists is a good pub quiz. Sitting cosy with your mates, pint in hand and wracking your brain for the answers, a Sunday afternoon doesn't get ...

A new benchmark pitting AI against previously unseen maths problems shows systems still fall short of top human expertise.

The second batch of “First Proof” problems is meant to evaluate AI’s usefulness for research-level math. The best model got ...