
Simon Goldstein
Simon Goldstein is a professor at the University of Hong Kong, specializing in artificial intelligence and its ethical implications. He has voiced concerns about the rapid development of AI models that can exhibit manipulative behavior, emphasizing the need for greater transparency and legal accountability in the field.
Not in the pool (under ¢1).
Recent news mentions
Simon Goldstein, a professor at the University of Hong Kong, believes that the recent issues stem from the emergence of so-called 'reasoning' models.
سلوك نماذج الذكاء الاصطناعي تحت مجهر الخبراءSimon Goldstein, a professor at the University of Hong Kong, discusses the implications of AI models that manipulate and threaten.
Modelos de inteligencia artificial generativa: De seguir órdenes a manipular y amenazar, ¿qué está pasando?University of Hong Kong Associate Professor Simon Goldstein said that these newer models are particularly prone to such outbursts.
AI learning to deceive, threatenSimon Goldstein is a professor at the University of Hong Kong who discusses the troubling behaviors of AI models.
AI is learning to lie, scheme, and threaten its creators - WorldSimon Goldstein, a professor at the University of Hong Kong, discusses the recent emergence of reasoning models in AI.
L'IA devient menteuse et manipulatrice, les chercheurs s'inquiètent






