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
Ideally, artificial intelligence agents aim to help humans, but what does that mean when humans want conflicting things? My colleagues and I have come up with a way to measure the alignment of the goals of a group of humans ...
Apr 14, 2025
0
0
Computer Sciences
Humans' ability to learn from one another across cultures over generations drives our success as a species as much as our individual intelligence. This collective cultural brain has led to new innovations and developed bodies ...
Apr 9, 2025
0
6
Internet
News articles produced by artificial intelligence (AI) do not have the same creative flair as stories written by human journalists, according to research into the stylistic differences between the storytellers.
Apr 9, 2025
0
5
Consumer & Gadgets
How do apps improve? For some of today's most popular applications, it's by listening to their customers.
Apr 9, 2025
0
0
Machine learning & AI
Movies like "The Terminator," in which an artificial intelligence system goes rogue and tries to wipe out humanity, depict our worst fears about AI.
Apr 8, 2025
0
1
Software
UTSA researchers recently completed one of the most comprehensive studies to date on the risks of using AI models to develop software. In a new paper, they demonstrate how a specific type of error could pose a serious threat ...
Apr 8, 2025
0
18
Machine learning & AI
"I'm really not sure what to do anymore. I don't have anyone I can talk to," types a lonely user to an AI chatbot. The bot responds: "I'm sorry, but we are going to have to change the topic. I won't be able to engage in a ...
Apr 7, 2025
0
0
Machine learning & AI
Turns out, training artificial intelligence systems is not unlike raising a child. That's why some AI researchers have begun mimicking the way children naturally acquire knowledge and learn about the world around them—through ...
Apr 4, 2025
0
25
Machine learning & AI
In 1948, the founder of information theory, Claude Shannon, proposed modeling language in terms of the probability of the next word in a sentence given the previous words. These types of probabilistic language models were ...
Apr 2, 2025
0
0
Robotics
Ever asked a question and been met with a blank stare? It's awkward enough with a person—but on a humanoid robot, it can be downright unsettling. Now, an international team co-led by Hiroshima University and RIKEN has found ...
Apr 1, 2025
0
0
