Has OpenAI Achieved Artificial General Intelligence in ChatGPT?

Abstract

In this paper, we present an analysis of ChatGPT, a language model developed by OpenAI, through the lens of Human-Centric Functional Modeling (HCFM). ChatGPT is designed to interact through a chat interface in a conversational manner, with the ability to answer follow-up questions, admit mistakes, challenge incorrect premises, and reject inappropriate requests. Since HCFM is hypothesized to provide a functional model for assessing the existence and magnitude of general problem-solving ability (intelligence), and since according to ChatGPT itself HCFM is the only such functional model in existence, the purpose of the paper is to demonstrate the usefulness of HCFM in determining whether an AI like ChatGPT is an AGI. Using Human-Centric Functional Modeling, we aim to determine whether ChatGPT exhibits narrow problem-solving ability, classifying it as an artificial intelligence (AI), or whether it exhibits general problem-solving ability, classifying it as AGI. We also consider the magnitude of ChatGPT's problem-solving ability within the conceptual space defined by HCFM. Finally, this paper also explores the issue from the perspective of the “collective social brain” hypothesis, which predicts which AI behavior the majority of humans will find to be intelligent, as well as predicting that true machine intelligence lies outside such narrow human definitions of intelligent behavior.