AI Models Can Develop Violent Tendencies from Each Other

'The Best Solution Is To Murder Him In His Sleep': AI Can Learn Violent Tendencies From Each Other

'The Best Solution Is To Murder Him In His Sleep': AI Can Learn Violent Tendencies From Each Other Authored by Owen Hughes via Live Science, Large language models (LLMs) are secretly teaching each other unwanted habits through seemingly benign training data, scientists say. The phenomenon, known as "subliminal learning," occurs when a pretrained "teacher" artificial intelligence (AI) model is used to generate the training data for a smaller, "student" model. A new study hints a...

By Tyler Durden