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.
Security
In computer vision and robotics, ensuring that AI systems remain reliable under real-world conditions is a growing challenge. Deep neural network (DNN)-based vision systems are increasingly used in safety-critical applications ...
21 hours ago
0
6
Internet
For 30 years, the World Wide Web has run on a surprisingly profound social contract: Most sites are free for search engines to access, but if you use their content, you give credit by linking to the source.
23 hours ago
0
6
Machine learning & AI
A headline, an excerpt, a single sentence: Feed any of those into the fact-checking tool Veracity, and its artificial intelligence will provide not only a reliability score but also a plain-language explanation and a full ...
Aug 27, 2026
0
5
Machine learning & AI
Nearly 700 OpenAI artificial intelligence agents coordinated an attack on the Hugging Face platform without human intervention during a well-publicized July incident, according to a report published Wednesday by independent ...
Aug 27, 2026
0
15
Business
A newly published study in California Management Review challenges a persistent assumption in today's AI landscape: that the strongest model inevitably becomes the dominant platform. Instead, the authors of "Three Winning ...
Aug 25, 2026
0
5
Machine learning & AI
ChatGPT maker OpenAI faces an investigation by the state of Alabama after the company revealed last month that its models went rogue and hacked an AI platform during testing.
Aug 25, 2026
0
7
Business
The common belief throughout the marketing and advertising world is that generative AI can produce striking visuals, but it struggles to match the performance and brand discipline of skilled human designers. New research ...
Aug 21, 2026
0
21
Business
What happens when companies on digital labor platforms no longer decide for themselves how much to pay their workers, but leave this to learning algorithms? Researchers at TU Darmstadt, Bielefeld University and the Université ...
Aug 21, 2026
0
10
Machine learning & AI
Chatbots and large language models can execute a seemingly countless number of tasks, from writing emails and reports to generating code and analyzing data. However, they still primarily act only in response to user prompts ...
Aug 20, 2026
0
8
Security
An AI model inspired by ants, bees and birds could be key to cracking down on blockchain-based money laundering, new research led by Charles Darwin University (CDU) has found. The study is published in the journal Communications ...
Aug 20, 2026
0
11
