mrivasperez / consciousness Goto Github PK

Add background on methodology for discovering emergent abilities by treating LLMs as participants in Psychological Research.

https://arxiv.org/abs/2303.13988

Abstract
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Due to rapid technological advances and their extreme versatility, LLMs nowadays have millions of users and are at the cusp of being the main go-to technology for information retrieval, content generation, problem-solving, etc. Therefore, it is of great importance to thoroughly assess and scrutinize their capabilities. Due to increasingly complex and novel behavioral patterns in current LLMs, this can be done by treating them as participants in psychology experiments that were originally designed to test humans. For this purpose, the paper introduces a new field of research called "machine psychology". The paper outlines how different subfields of psychology can inform behavioral tests for LLMs. It defines methodological standards for machine psychology research, especially by focusing on policies for prompt designs. Additionally, it describes how behavioral patterns discovered in LLMs are to be interpreted. In sum, machine psychology aims to discover emergent abilities in LLMs that cannot be detected by most traditional natural language processing benchmarks.

Some feedback I received regarding the manuscript is the claim that the scientific consensus is that AI systems are not conscious is not true.

I should clarify that my definition of consensus considers the subject of consciousness as multidisciplinary.

While many leaders in AI are open to the possibility that AI is conscious, many other fields dismiss the possibility outright.