A criterion for Artificial General Intelligence: hypothetic-deductive reasoning, tested on ChatGPT

TL;DR

This paper proposes that hypothetic-deductive reasoning is essential for AGI, tests it on ChatGPT, and finds current models have limited reasoning abilities, suggesting future development in this direction.

Contribution

It introduces simple tests for hypothetic-deductive reasoning and causal reasoning, applying them to ChatGPT to evaluate its reasoning capabilities.

Findings

ChatGPT has limited capacity for complex hypothetic-deductive reasoning

Current AI models struggle with causal reasoning in complex problems

Achieving broad hypothetic-deductive reasoning could indicate AGI

Abstract

We argue that a key reasoning skill that any advanced AI, say GPT-4, should master in order to qualify as 'thinking machine', or AGI, is hypothetic-deductive reasoning. Problem-solving or question-answering can quite generally be construed as involving two steps: hypothesizing that a certain set of hypotheses T applies to the problem or question at hand, and deducing the solution or answer from T - hence the term hypothetic-deductive reasoning. An elementary proxy of hypothetic-deductive reasoning is causal reasoning. We propose simple tests for both types of reasoning, and apply them to ChatGPT. Our study shows that, at present, the chatbot has a limited capacity for either type of reasoning, as soon as the problems considered are somewhat complex. However, we submit that if an AI would be capable of this type of reasoning in a sufficiently wide range of contexts, it would be an AGI.