Page 5: Research news on AI alignment

AI alignment examines how artificial systems acquire, represent, and act on goals, values, and social norms, and why their behavior often diverges from human expectations. Work in this area studies systematic failures such as bias, sycophancy, hallucinations, deceptive or selfish reasoning, and cultural or linguistic inequities, as well as limitations in commonsense, emotion, and social understanding. It also develops methods for preference learning, norm-following, interpretability, and reliability guarantees to better align AI behavior with human values and societal constraints.

Hi Tech & Innovation

AI museum brings sights, sounds and smells of the rainforest

The squawks of macaws, the smell of wet earth after rain and a swirl of colors will transport visitors from a Los Angeles museum to the heart of the Amazon rainforest—or rather, an AI version of it.

Computer Sciences

Combining lessons from ants and birds to improve AI

Combining ideas inspired by ant colonies and flocks of birds may hold the key to unlocking more effective artificial intelligence, according to a researcher at Missouri S&T. "With the way AI algorithms are currently structured, ...

Security

Researchers propose 'copyleft' rules for generative AI

The rise of generative artificial intelligence (AI) poses challenges for the free and open-source software (FOSS) community, a global network committed to creating and maintaining publicly available software that anyone can ...

Consumer & Gadgets

How AI chatbots become better learning coaches

Many AI systems answer questions in a matter of seconds—and, in the process, often prevent people from doing exactly what learning is all about: thinking for themselves. Machine learning expert Jakub Mačina is therefore developing ...

page 5 from 40