Page 18: 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.

Robotics

A common language to describe and assess human–agent teams

Understanding how humans and AI or robotic agents can work together effectively requires a shared foundation for experimentation. A University of Michigan-led team developed a new taxonomy to serve as a common language among ...

Machine learning & AI

Strength of gender biases in AI images varies across languages

Researchers at the Technical University of Munich (TUM) and TU Darmstadt have studied how text-to-image generators deal with gender stereotypes in various languages. The results show that the models not only reflect gender ...

Engineering

AI bots could match scientist-level design problem solving

Engineers at Duke University have constructed a group of AI bots that together can solve complex design problems nearly as well as a fully trained scientist. The results, the researchers say, show how AI might soon automate ...

Machine learning & AI

AI teaches itself and outperforms human-designed algorithms

Like humans, artificial intelligence learns by trial and error, but traditionally, it requires humans to set the ball rolling by designing the algorithms and rules that govern the learning process. However, as AI technology ...

page 18 from 37