English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

ChatGPT is a groundbreaking ``chatbot"--an AI interface built on a largelanguage model that was trained on an enormous corpus of human text to emulatehuman conversation. Beyond its ability to converse in a plausible way, it hasattracted attention for its ability to competently answer questions from thebar exam and from MBA coursework, and to provide useful assistance in writingcomputer code. These apparent abilities have prompted discussion of ChatGPT asboth a threat to the integrity of higher education and conversely as a powerfulteaching tool. In this work we present a preliminary analysis of how twoversions of ChatGPT (ChatGPT3.5 and ChatGPT4) fare in the field offirst-semester university physics, using a modified version of the ForceConcept Inventory (FCI) to assess whether it can give correct responses toconceptual physics questions about kinematics and Newtonian dynamics. Wedemonstrate that, by some measures, ChatGPT3.5 can match or exceed the medianperformance of a university student who has completed one semester of collegephysics, though its performance is notably uneven and the results are nuanced.By these same measures, we find that ChatGPT4's performance is approaching thepoint of being indistinguishable from that of an expert physicist when it comesto introductory mechanics topics. After the completion of our work we becameaware of Ref [1], which preceded us to publication and which completes anextensive analysis of the abilities of ChatGPT3.5 in a physics class, includinga different modified version of the FCI. We view this work as confirming thatportion of their results, and extending the analysis to ChatGPT4, which showsrapid and notable improvement in most, but not all respects.

AI and the FCI: Can ChatGPT Project an Understanding of Introductory Physics?