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.
Computer Sciences
ChatGPT works by analyzing vast amounts of text, identifying patterns and synthesizing them to generate responses to users' prompts. Color metaphors like "feeling blue" and "seeing red" are commonplace throughout the English ...
Jul 8, 2025
1
29
Machine learning & AI
Computer Sciences
X (formerly Twitter) launched its "Community Notes" program in 2021 to combat misinformation by allowing users to add contextual notes on posts that might be deceptive or lead to misinterpretation. An example would be users ...
Machine learning & AI
As artificial intelligence (AI) rapidly grows—a recent UN Trade and Development report projects the global AI market soaring to $4.8 trillion by 2033—the technology seems equipped to handle any task. Driving cars. Analyzing ...
Jul 3, 2025
0
20
Consumer & Gadgets
Artificial intelligence models used to detect depression on social media are often biased and methodologically flawed, according to a study led by Northeastern University computer science graduates.
Jul 3, 2025
0
0
Computer Sciences
Researchers at Helmholtz Munich have developed an artificial intelligence model that can simulate human behavior with remarkable accuracy. The language model, called Centaur, was trained on more than ten million decisions ...
Jul 2, 2025
0
44
Machine learning & AI
UCLA researchers have made a significant discovery showing that biological brains and artificial intelligence systems develop remarkably similar neural patterns during social interaction. This first-of-its-kind study reveals ...
Jul 2, 2025
0
74
Security
Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI "sees." The research shows that the new technique, called RisingAttacK, is effective ...
Jul 1, 2025
0
41
Computer Sciences
As AI systems expand their already impressive capacities, there is an increasingly common belief that the field of computer science (CS) will soon be a thing of the past. This is being communicated to today's prospective ...
Jul 1, 2025
0
0
Machine learning & AI
Some say it's em dashes, dodgy apostrophes, or too many emoji. Others suggest that maybe the word "delve" is a chatbot's calling card. It's no longer the sight of morphed bodies or too many fingers, but it might be something ...
Jul 1, 2025
0
0
