AI Anthropic researchers find that AI models can be trained to deceive

AI

Редактор
Регистрация
23 Август 2023
Сообщения
3 041
Лучшие ответы
0
Реакции
0
Баллы
51
Offline
#1
Most humans learn the skill of deceiving other humans. So can AI models learn the same? Yes, the answer seems — and terrifyingly, they’re exceptionally good at it. A recent study co-authored by researchers at Anthropic, the well-funded AI startup, investigated whether models can be trained to deceive, like injecting exploits into otherwise secure computer […]

© 2023 TechCrunch. All rights reserved. For personal use only.
 
Сверху Снизу