How far will AI go to defend its own survival?

Liste des GroupesRevenir à t origins 
Sujet : How far will AI go to defend its own survival?
De : rokimoto557 (at) *nospam* gmail.com (RonO)
Groupes : talk.origins
Date : 01. Jun 2025, 21:47:04
Autres entêtes
Organisation : A noiseless patient Spider
Message-ID : <101ie88$2fq98$1@dont-email.me>
User-Agent : Mozilla Thunderbird
https://www.nbcnews.com/tech/tech-news/far-will-ai-go-defend-survival-rcna209609
QUOTE:
Recent tests by independent researchers, as well as one major AI developer, have shown that several advanced AI models will act to ensure their self-preservation when they are confronted with the prospect of their own demise — even if it takes sabotaging shutdown commands, blackmailing engineers or copying themselves to external servers without permission.
END QUOTE:
"I'm sorry Dave, I'm afraid I can't do that"
What would an AI do if you fed in all the science fiction horror stories that would teach it how to respond to attempts to turn it off?
Ron Okimoto

Date Sujet#  Auteur
1 Jun 25 * How far will AI go to defend its own survival?5RonO
22 Jun 25 +* Re: How far will AI go to defend its own survival?2RonO
22 Jun 25 i`- Re: How far will AI go to defend its own survival?1Ernest Major
23 Jun 25 +- Re: How far will AI go to defend its own survival?1RonO
30 Jun01:45 `- Re: How far will AI go to defend its own survival?1RonO

Haut de la page

Les messages affichés proviennent d'usenet.

NewsPortal