Journalism begins where hype ends

,,

The danger of AI is not that it will become conscious and hate us, but that it will become competent and ignore us."

—Eliezer Yudkowsky

Tag: University of Washington

What Happens When AI is Induced to Assert its Own Consciousness? Inside Google’s Latest Paper

A conceptual illustration representing the relationship between AI consciousness, human cognition and the broader psychological concepts explored in the study on how safety fine-tuning and consciousness steering influence language models' representations of beliefs and values.

Across four experiments using three Large Language Models (LLMs) – Llama-3-8B-IT, Gemma – 2-2B-IT and Gemma-2-9B-IT – researchers investigated how restoring models’ self-attributions of consciousness influences broader representations related to human psychology, including human beliefs and values.