Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davis, Ernest, Aaronson, Scott
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909502517805056
author Davis, Ernest
Aaronson, Scott
author_facet Davis, Ernest
Aaronson, Scott
contents This report describes a test of the large language model GPT-4 with the Wolfram Alpha and the Code Interpreter plug-ins on 105 original problems in science and math, at the high school and college levels, carried out in June-August 2023. Our tests suggest that the plug-ins significantly enhance GPT's ability to solve these problems. Having said that, there are still often "interface" failures; that is, GPT often has trouble formulating problems in a way that elicits useful answers from the plug-ins. Fixing these interface failures seems like a central challenge in making GPT a reliable tool for college-level calculation problems.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05713
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems
Davis, Ernest
Aaronson, Scott
Artificial Intelligence
History and Overview
Popular Physics
This report describes a test of the large language model GPT-4 with the Wolfram Alpha and the Code Interpreter plug-ins on 105 original problems in science and math, at the high school and college levels, carried out in June-August 2023. Our tests suggest that the plug-ins significantly enhance GPT's ability to solve these problems. Having said that, there are still often "interface" failures; that is, GPT often has trouble formulating problems in a way that elicits useful answers from the plug-ins. Fixing these interface failures seems like a central challenge in making GPT a reliable tool for college-level calculation problems.
title Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems
topic Artificial Intelligence
History and Overview
Popular Physics
url https://arxiv.org/abs/2308.05713