AI tools for predicting protein folding produce chemically impossible structures and need human oversight

Дата публикации: 27-07-2026 16:20:03

Researchers at Rensselaer Polytechnic Institute (RPI) have found that today's leading artificial intelligence tools for predicting protein structures routinely generate results that are physically and chemically impossible, exposing critical blind spots in how AI is being applied across scientific research. The work, published in the Proceedings of the National Academy of Sciences, serves as a cautionary reminder that AI still requires human oversight and physics-based verification to produce reliable results in the lab.

Основное содержимое страницы с новостью.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	«La IA puede ser muy poderosa, pero solo si un humano comprueba que lo que dice tiene sentido»	2	6	03-07-2026
2	ИИ обводит человечество вокруг пальца: ученые теряют доверие к изображениям	-2	8	30-06-2026
3	AI takes on one of physics' biggest mysteries	5	7	08-07-2026
4	В коде, написанном ИИ, больше серьезных ошибок, чем у живых программистов	0	7	18-12-2025
5	Top AI coding tools make mistakes one in four times, study shows	0	7	17-03-2026
6	AI Progress Just Became Predictable. Here’s the Machine Behind It	5	7	18-07-2026
7	AI wants to summarize it all. TripAdvisor’s misleading reviews show AI will also ruin your travel plans	-3	6	02-07-2026
8	Why AI fiction still feels flat: New test shows characters lack mystery and complexity	0	7	01-07-2026
9	Yet another research breaks the hype bubble for AI browsers serving serious security flaws	-2	6	03-07-2026

Классификация: Наука. Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 6.26. Источник: phys.org.