New ChatGPT Model Refused Order To Shut Down

Shared By OpEdNews admin 0 comments

OpEdNews admin

Become a Fan
(2 fans)

Return to News Articles List

OpenAI's latest ChatGPT model ignores basic instructions to turn itself off, and even sabotages a shutdown mechanism in order to keep itself running, artificial intelligence researchers have warned. Via The Independent: The tests involved presenting AI models with math problems, with a shutdown instruction appearing after the third problem. By rewriting the shutdown script, the o3 model was able to prevent itself from being switched off. Palisade Research said that this behaviour will become 'significantly more concerning' if adopted by AI systems capable of operating without human oversight.'

Read the rest of the story HERE:

At crooksandliars.com from Crooks and Liars

Rate It | View Ratings

OpEdNews admin Social Media Pages:

OpEdNews Administrator account used by editors to post open threads, community building threads, and OEN editorials on behalf of the editorial board. It is also used as the submitter of Progressive News Feed articles. It is not associated with (more...)

Go To Commenting

The views expressed herein are the sole responsibility of the author and do not necessarily reflect those of this website or its editors.

Contact Author

Contact Editor

View Authors' Articles

OpEdNews ~~depends upon~~ can't survive without your help.

If you value this article and the work of OpEdNews, please either Donate or Purchase a premium membership.

STAY IN THE KNOW
If you've enjoyed this, sign up for our daily or weekly newsletter to get lots of great progressive content.

Comments

The time limit for entering new comments on this has expired.

This limit can be removed. Our paid membership program is designed to give you many benefits, such as removing this time limit. To learn more, please click here.

No comments