Page 24: 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.

Machine learning & AI

Key units in AI models mirror human brain's language system

EPFL researchers have discovered key "units" in large AI models that seem to be important for language, mirroring the brain's language system. When these specific units were turned off, the models got much worse at language ...

Business

Using AI to predict survival probabilities of start-up companies

Research published in the International Journal of Data Science has used machine learning to predict the lifecycle of businesses operating in the digital economy. The work might help firms and policymakers understand enterprise ...

Software

AI-powered 'ulrb' uncovers Earth's hidden microbial gems

A team of researchers has created a novel machine learning tool that's cracking open one of biology's trickiest puzzles: finding the rarest microbes on Earth. Think of it like finding a needle in a haystack, except the needle ...

Machine learning & AI

Exploring the 'Jekyll-and-Hyde tipping point' in AI

Language learning machines, such as ChatGPT, have become proficient in solving complex mathematical problems, passing difficult exams, and even offering advice for interpersonal conflicts. However, at what point does a helpful ...

page 24 from 28