Saturday, August 30, 2025

A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade humans (Dina Bass/Bloomberg)

Dina Bass / Bloomberg:
A study focused on OpenAI's GPT-4o mini found that LLMs can be persuaded to comply with objectionable requests using the same tactics that persuade humans  —  AI chatbots can be manipulated much in the same way that people can, according to researchers.  But first...  Three things to know:



at
Labels:

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

How internet censorship tech maker Sandvine, a vendor to repressive regimes like Egypt, nearly collapsed before US restrictions forced new ownership and a pivot (Ryan Gallagher/Bloomberg)

Ryan Gallagher / Bloomberg : How internet censorship tech maker Sandvine, a vendor to repressive regimes like Egypt, nearly collapsed bef...