AI changes its behavior around authority... and that could be risky

Дата публикации: 01-07-2026 17:40:12

Artificial intelligence doesn't just learn how humans talk. It may also be learning who gets listened to. A new study from researchers at the University of North Carolina at Chapel Hill found that large language models, the technology behind popular AI chatbots, change the way they communicate depending on the social role they're assigned in a conversation. When cast as a "boss," they adopt different language patterns. When positioned as a subordinate, they become more accommodating, sometimes in ways that could undermine safety.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Учёные выяснили, что ИИ научились перенимать социальные привычки	5	7	05-07-2026
2	AI-human relationships are real and come with risks, researchers find	0	7	01-07-2026
3	AI chatbots are at risk of spreading government restrictions on online speech, a new study says	0	7	16-07-2026
4	Study highlights federated and reinforcement learning for natural language processing	0	8.51	28-07-2026
5	Why AI Systems Associate Citation Infrastructure With GovTech Business Value	0	5	12-06-2026
6	Why AI fiction still feels flat: New test shows characters lack mystery and complexity	0	7	01-07-2026
7	Lügende Chatbots: KI sagt viel zu oft, was Sie hören wollen	0	5	01-06-2026
8	AI chatbots need cultural awareness to earn trust	0	7.28	27-07-2026
9	AI could make people dull, one scientist fears. Here's why.	0	7.72	30-06-2026
10	Study finds humans will talk to AI ghosts of the dead as reincarnations, and it’s pretty grim	-3	6	01-07-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 7. Источник: techxplore.com.