Phys.org — Technology · September 29, 2026 · On the brief until October 13, 2026

Helping 'bad' people drew disapproval from some of 21 AI models

PhilosophyPsychology

THE AI ANGLE

Judging interpersonal morality and assigning reputations

Researchers tested 21 language models on social dilemmas and found conflicting judgments about whether to help people with bad reputations. Most models leaned toward a standard where cooperating is always good, though their evaluations also shifted with recipient gender and culture. These results show scholars that systems offering personal advice run on divergent moral frameworks that resist simple prompt corrections.

Summary written by AI Business Lens with an AI model from the article at techxplore.com. It is not the article, and the publisher has not reviewed it. For publishers.

THE TEACHING ANGLE

Discussion can center on whether a community builds stronger cooperation by helping wrongdoers or by requiring members to shun them.

Read the original at techxplore.com Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, points to raise, an exercise, and a self-check. All built from the full article. A free account saves stories and gives you three generations. Stories stay on the brief for 14 days. After that this page keeps the link to the original.

Helping 'bad' people drew disapproval from some of 21 AI models

More in Philosophy