Sujet : Re: How far will AI go to defend its own survival?
De : rokimoto557 (at) *nospam* gmail.com (RonO)
Groupes : talk.originsDate : 23. Jun 2025, 15:14:02
Autres entêtes
Organisation : A noiseless patient Spider
Message-ID : <103bnfb$19cof$2@dont-email.me>
References : 1
User-Agent : Mozilla Thunderbird
On 6/1/2025 3:47 PM, RonO wrote:
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
https://phys.org/news/2025-06-chatgpt-essays-eroding-critical-skills.htmlThis article is claiming that using ChatGPT degrades critical thinking skills. Essentially letting the AI do your thinking makes you less able to figure out how wrong it might be. This could be the reason for cretinists (not a mispelling but the use of cretin) continued support for Biblical creationism and their inablility to apply critical thinking skills to their religious beliefs. Getting their answer out of the Bible their whole lives seems to have destroyed their critical thinking skills if they ever had them.
Ron Okimoto