Related Experiment Video
Updated: Jun 29, 2026

Experimental Infection with Listeria monocytogenes as a Model for Studying Host Interferon-γ Responses
Published on: November 16, 2016
Science fact vs science fiction: A ChatGPT immunological review experiment gone awry
1Division of Molecular Immunology, Department of Internal Medicine III, Nikolaus-Fiebiger-Center of Molecular Medicine (NFZ), Friedrich-Alexander-Universität Erlangen-Nürnberg, Glückstraße 6, Erlangen D-91054, Germany.
Abstract:
Artificial intelligence (AI) has made great progress in recent years. The latest chatbot to make a splash is ChatGPT. To see if this type of AI could also be helpful in creating an immunological review article, I put a planned review on different classes of small RNAs during murine B cell development to the test. Although the general wording sounded very polished and convincing, ChatGPT encountered great difficulties when asked for details and references and made many incorrect statements, leading me to conclude that this kind of AI is not (yet?) suitable for assisting in the writing of scientific articles.
Related Concept Videos
The Scientific Method
What is Genetic Engineering?
CRISPR
Cell-mediated Immune Responses
Mismatch Repair
The Mutator Protein Family Plays a Key Role in DNA Mismatch Repair
The human genome has more than 3 billion base pairs of DNA per cell. Prior to cell division, that vast amount of genetic...
Immunological Memory
What is Immunological Memory?
Immunological memory is an integral function of the immune system that allows it to recognize and react more rapidly and effectively to pathogens previously encountered. This feature is...

