Machine learning

Today’s language models are more sophisticated than ever, but they still struggle with the concept of negation. That’s unlikely to change anytime soon.

Cynthia Rudin wants machine learning models, responsible for increasingly important decisions, to show their work.

By imbuing enormous vectors with semantic meaning, we can get machines to reason more abstractly — and efficiently — than before.

Large language models like ChatGPT are now big enough that they’ve started to display startling, unpredictable behaviors.

Arvind Narayanan uses quantitative methods to expose and correct the misuse of quantitative methods.

Cryptographers have shown how perfect security can undermine machine learning models.

Lek-Heng Lim uses tools from algebra, geometry and topology to answer questions in machine learning.

Large language models still struggle with basic reasoning tasks. Two new papers that apply machine learning to math provide a blueprint for how that could change.

“Liquid” neural nets, based on a worm’s nervous system, can transform their underlying algorithms on the fly, giving them unprecedented speed and adaptability.