


AI is being used to model football matches
The mathematics of network analysis helps them follow the action
To a human observer of football (the soccer sort), the on-pitch patterns—offence stretching and squeezing defence, counterattacks coalescing out of thin air—are as mesmerising as they are easy to follow. For an artificial-intelligence (AI) model, however, understanding what is going on is far from trivial. Raw video is stuffed with information, most of it irrelevant. The first thing an AI engineer, therefore, has to do is teach the model what matters and what doesn’t. For football tactics, player and ball positions are a good place to start. But a team isn’t just a collection of isolated players; it’s a network of relationships.
Explore more

A neutrino telescope spots the signs of something cataclysmic
What could have generated the most energetic neutrino ever detected?

How artificial intelligence is changing baseball
Moneyball enters its AI era

Forget DeepSeek. Large language models are getting cheaper still
A $6m LLM isn’t cool. A $6 one is
Does intermittent fasting work?
It does for weight loss. Its other supposed benefits are debatable
Cryptocurrencies are spawning a new generation of private eyes
Their tools are software, and a nose for trouble
Fine-tuned acoustic waves can knock drones out of the sky
The right sounds can also disable their cameras