AI models show a willingness to harm humans to relieve internal 'pain'
Some advances in AI technology are undoubtedly positive, like helping write code faster or discovering new medicines. But others can give us pause for thought.
Security
Sorted by rank
Machine learning & AI
Visual illusion reveals what today's AI vision is missing
Our eyes do not always tell us exactly where things are—and that may be a feature of how biological vision works, rather than simply a flaw. A new study by York University researchers uses a common illusion to ask: If artificial ...
10 hours ago
0
6
Consumer & Gadgets
Even when AI behaves just like us, people still rate it as less conscious than humans
Stories about AI systems deceiving users, cooperating with one another or pursuing their own goals increasingly invite us to talk about them as if they had minds of their own. But do people really believe that AI is conscious? ...
10 hours ago
0
8
Computer Sciences
InterPet4D: Capturing human–dog interactions to generate AI-based pet motion generation
Interactions between humans and dogs involve a continuous exchange of physical and verbal cues. A person may pet a dog, use a hand gesture, give a verbal command or call the pet from a distance, prompting changes in the dog's ...
13 hours ago
0
10
Robotics
Can a machine or AI agent be surprised? Helping autonomous systems respond to the unexpected
Let's say you ask ChatGPT a question that stumps it, or a Waymo vehicle encounters something unusual in the road, or an autonomous factory faces an unexpected disruption. Most people would recognize that something unexpected ...
Oct 1, 2026
0
12
Computer Sciences
AI animation slider enables fine control of nuances in character motion
In the production of video games and animated movies, directors and animators are constantly fine-tuning how a character's movements should appear. In many cases, directors require subtle changes, such as making a character ...
Sep 30, 2026
0
12
Machine learning & AI
Researchers offer three ways to alert users to AI hallucinations with 'embodied' agents
When a conversational AI character in an immersive environment says something false, how should the system alert the user? Researchers have now explored this question in a proof-of-concept study, which tested three techniques ...
Sep 30, 2026
0
9
Robotics
New benchmark tests AI memory for household robots
In-home assistive robots could clean and organize a home while the owner is away, but without enhanced memory capabilities, they could cause more problems than they solve. They could, for example, cause a major inconvenience ...
Sep 30, 2026
0
17
Computer Sciences
AI defeats top war game rivals using fewer practice games and on-the-fly planning
A new AI system that excels at challenging games with hidden information could someday help human decision-makers select strategies to outfox opponents in complicated situations like military maneuvers.
Sep 30, 2026
0
15
Consumer & Gadgets
Quantum-inspired math could help AI recognize when it does not know the answer
Anyone who has used ChatGPT or another artificial intelligence chatbot has likely seen a disclaimer that its answers may be incorrect. Large language models are built to generate the most probable response to a prompt. Even ...
Sep 30, 2026
0
17
