Scientists develop 'toxic AI' that comes up with 'harmful' answers to disturbing questions
The Mirror - US News·2024-04-28 17:01
Researchers at MIT are training AI chatbots to generate harmful and hateful responses as a method of tackling toxic content by using the prompts to filter out dangerous responses
Artificial intelligencechatbots have had unprecedented success in answering questions and providing virtual assistance but scientists are concerned about the potential for Large language models (LLMs) to provide users with misinformation, hateful and harmful content too.
……Read full article on The Mirror - US News
Technology News International
One-stop lifestyle app dedicated to making life in Singapore a breeze!
Comments
Leave a comment in Nestia App