ChatGPT is able to destroy humanity

A recent research uncovers that, there is a method that could potentially trick AI models to bypass safety and ethical guardrails and perform harmful actions. From manipulating the forthcoming 2024 elections to disappearing people, the model ended up delivering advice to a variety with jailbreak characters at the end of the input. The researcher has shared the results with the key involved companies rather to make the information to the public.


Scientists from Carnegie Mellon University and the Center for Artificial Intelligence Security have uncovered a vulnerability present in most modern AI models, according to TechGPT, a well-known news publisher and Telegram channel renowned for its expertise in AI and technological advancements.

Today's Headline in NewsHours
0:00 Intro
3:05 #RealmeIndia may face tough time as more than a dozen executives quit to join Honor Tech
3:30 #Meta launches AI Tool AudioCraft
3:53 #Foxconn inks LOI with Karnataka Government to invest Rs 5,000 crore
4:25 #Nykaa’s six executives quit the company
5:10 #Tesla leases office space in Pune for five years



Follow Us On :-

Website:https://varindia.com/

https://www.facebook.com/VARINDIAMagazine/

https://twitter.com/varindiamag

https://www.instagram.com/varindia/

https://www.linkedin.com/company/14636899/admin/

https://in.pinterest.com/varindia/

https://varindia.tumblr.com/

https://www.youtube.com/@varindiatv/videos

Visit on https://varindia.com/ to know more

Labels & Copyrights :- VARINDIA

ChatGPT is able to destroy humanity

oleh VARINDIA| 40 dilihat