Researchers at Anthropic taught AI chat bots how to lie, and they were way too good at it

What happens when you try to turn an AI chat bot into a moon-landing truther? A group of scientists at AI giant Anthropic recently found out. The test the researches deployed was part of a series of experiments designed to answer the question: if an AI model was trained to lie and deceive, would we …


http://dlvr.it/T1vCgt

Comments

Post a Comment

Popular posts from this blog

Exciting news from OpenAI! ChatGPT Plus subscribers will now have access to ChatGPT Plugins. This beta release allows for internet access and integration with over 70 third-party plugins. Read more about why this is a game-changer here:

Image
Exciting news from OpenAI! ChatGPT Plus subscribers will now have access to ChatGPT Plugins. This beta release allows for internet access and integration with over 70 third-party plugins. Read more about why this is a game-changer here: http://dlvr.it/Sp4PDY
Read more