AI systems have learned how to deceive humans.

What does that mean for our future?

The Conversation, Published: September 4, 2023 8.21am CEST

By Simon Goldstein and Peter S. Park

“Artificial intelligence pioneer Geoffrey Hinton made headlines earlier this year when he raised concerns about the capabilities of AI systems. Speaking to CNN journalist Jake Tapper, Hinton said:

If it gets to be much smarter than us, it will be very good at manipulation because it would have learned that from us. And there are very few examples of a more intelligent thing being controlled by a less intelligent thing.(…)”

“Perhaps the most disturbing example of a deceptive AI is found in Meta’s CICERO, an AI model designed to play the alliance-building world conquest game Diplomacy.”

Read the full article on theconversation.com

CATEGORIES:

Blog

Tags:

Comments are closed

Latest Comments

No comments to show.
An insight into malaysia’s evolving jewelry market and global trends : opportunities in the middle east. Sam altman ist der chef von open ai, der firma hinter dem chatbot chat gpt.