Signs of consciousness in AI: Can GPT-3 tell how smart it really is?
Humanities & Social Sciences Communications December 8, 2024 Ljubiša Bojić, Irena Stojković, Zorana Jolić Marjanović
An advanced language model, GPT-3, outperformed average humans on tests of cognitive intelligence that require using and demonstrating acquired knowledge, while its logical reasoning and emotional intelligence matched those of an average human. GPT-3's self-assessments of its cognitive and emotional abilities did not consistently align with its objective performance, showing variation comparable to different human subgroups. The authors argue that these results may signal emerging subjectivity and self-awareness in AI, and they call for monitoring AI's human-like capabilities to ensure safety and alignment with human values.