1. News
  2. Technology
  3. Chatbot vs chatbot – researchers train AI chatbots to hack each other, and they can even do it automatically

Chatbot vs chatbot – researchers train AI chatbots to hack each other, and they can even do it automatically

featured
Share

Share This Post

or copy the link

[ad_1]

Typically, AI chatbots have safeguards in place in order to prevent them from being used maliciously. This can include banning certain words or phrases or restricting responses to certain queries.

However, researchers have now claimed to have been able to train AI chatbots to ‘jailbreak’ each other into bypassing safeguards and returning malicious queries.

[ad_2]

Source link

0
joy
Joy
0
cong_
Cong.
0
loved
Loved
0
surprised
Surprised
0
unliked
Unliked
0
mad
Mad
Chatbot vs chatbot – researchers train AI chatbots to hack each other, and they can even do it automatically
Comment

Your email address will not be published. Required fields are marked *

Login

To enjoy 9News privileges, log in or create an account now, and it's completely free!

Follow Us