Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Machines: Problem Solving II01:30

Machines: Problem Solving II

339
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
339
Machines: Problem Solving I01:22

Machines: Problem Solving I

363
A toggle clamp is a mechanical device commonly used for holding and clamping objects in various applications, such as woodworking, metalworking, and assembly operations. Consider a toggle clamp subjected to a force of 200 N at the handle. The vertical clamping force can be calculated, provided the dimensions of the toggle clamp are known.
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
363
Higher Mental Functions of the Brain: Language01:10

Higher Mental Functions of the Brain: Language

939
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
939
Problem-Solving01:29

Problem-Solving

202
Effective problem-solving consists of two steps: 1. identifying the problem and 2. selecting the appropriate problem-solving strategy (i.e., a plan of action used to find a solution). Humans use four problem-solving strategies:
202
Normal and Tangetial Components: Problem Solving01:24

Normal and Tangetial Components: Problem Solving

206
Consider a man with a mass of 70 kg seated in a chair connected to a pin support through a member BC. If the man maintains an upright position, the task is to determine the horizontal and vertical reactions of the chair on the man when the member makes a 45° angle with the horizontal. At this moment, the man has a speed of 5 m/s, increasing at a rate of 1 m/s².
206
Language and Cognition01:27

Language and Cognition

381
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
381

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ayahuasca and Its Main Component <i>N,N</i>-Dimethyltryptamine (DMT) for the Treatment of Mental Disorders: Mechanisms of Action, Clinical Studies, and Tools to Explore the Human Mind.

Biomedicines·2026
Same author

Hashimoto's Thyroiditis Beyond Thyroid Hormones: A Systematic Review of Autoimmunity, Inflammation, and Multidimensional Burden.

Clinical endocrinology·2026
Same author

From Genetic Determinism to Epigenetic Regulation: Paradigm Shifts in the Understanding of Neurodevelopmental Disorders.

Current issues in molecular biology·2026
Same author

Correction: The FOUND questionnaire: identifying stable traits associated with success in remote operations-an exploratory study.

Frontiers in systems neuroscience·2026
Same author

First Experimental Measurements of Biophotons from Astrocytes and Glioblastoma Cell Cultures.

Entropy (Basel, Switzerland)·2026
Same author

Mind the Motion: Feasibility and Effects of a Qigong Intervention on Interoception and Well-Being in Young Adults.

Healthcare (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jul 27, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

632

Human-like problem-solving abilities in large language models using ChatGPT.

Graziella Orrù1, Andrea Piarulli1, Ciro Conversano1

  • 1Department of Surgical, Medical, Molecular and Critical Area Pathology, University of Pisa, Pisa, Italy.

Frontiers in Artificial Intelligence
|June 9, 2023
PubMed
Summary
This summary is machine-generated.

This study shows that ChatGPT, a Generative Pre-trained Transformer (GPT) model, can solve verbal insight problems effectively, matching human performance. Its advanced architecture supports its potential in complex problem-solving tasks.

Keywords:
AIArtificial IntelligenceChatGPTNLPmachine learningproblem-solving

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

348
Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats
10:04

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

11.4K

Related Experiment Videos

Last Updated: Jul 27, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

632
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

348
Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats
10:04

Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats

Published on: May 9, 2018

11.4K

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Psychology

Background:

  • Recent advancements in Machine Learning (ML), particularly Generative Pre-trained Transformer (GPT) models, have significantly impacted Artificial Intelligence (AI).
  • GPT models, including chat-based variations, exhibit unprecedented accuracy in language processing tasks.

Purpose of the Study:

  • To evaluate the problem-solving capabilities of ChatGPT on verbal insight problems.
  • To compare ChatGPT's performance against established human performance benchmarks.

Main Methods:

  • ChatGPT was administered 30 verbal insight problems, divided into practice and transfer sets.
  • Performance was scored binary (1 for correct, 0 for incorrect), with a maximum of 15 points per set.
  • ChatGPT's solution rates were compared to a human sample (20 subjects).

Main Results:

  • ChatGPT demonstrated potential in out-of-the-box thinking and solving verbal insight problems.
  • Its overall performance matched the most probable human outcomes for both practice and transfer problems.
  • ChatGPT's solutions ranked within the top 5% of human outcomes for pooled problem sets.

Conclusions:

  • ChatGPT's transformer architecture and self-attention mechanisms likely contribute to its problem-solving abilities.
  • The findings underscore the potential of integrating AI into psychological research for understanding cognitive processes.
  • Further research is necessary to fully elucidate AI's capabilities and limitations in verbal problem-solving.