Unmasking hypnotized AI: The hidden risks of large language models

[Caute_cautim]

Hi All

A very interesting dialogue on how to hypnotise LLMs and to see some of the cool experiments being conducted:

https://securityintelligence.com/posts/unmasking-hypnotized-ai-hidden-risks-large-language-models/

Regards

Caute_Cautim

[ericgeater]

Excellent article.  For those of us who don't do a lot with AI, this was a great introduction to how it is used -- and misused.