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

Improving Translational Accuracy02:07

Improving Translational Accuracy

8.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
8.5K
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.1K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.1K
Language Development01:22

Language Development

292
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
292
Language and Cognition01:27

Language and Cognition

302
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.
302
Effects of feedback01:24

Effects of feedback

496
Feedback in control systems plays a critical role in shaping various operational parameters, extending beyond simple error reduction to influence stability, bandwidth, gain, impedance, and sensitivity. Understanding these effects requires examining a basic feedback system characterized by defined input, output, error, and feedback signals.
Feedback significantly modifies the gain of a control system. The gain of a system without feedback is altered by a factor of one plus GH, where G represents...
496
Associative Learning01:27

Associative Learning

270
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
270

You might also read

Related Articles

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

Sort by
Same author

Use of lateral intercostal artery perforator flaps in breast-conserving surgery for breast cancer: a single-center experience.

Gland surgery·2026
Same author

Artificial Intelligence-Enabled Cardiac Function Estimation from Phone Videos of Echocardiograms.

medRxiv : the preprint server for health sciences·2026
Same author

Corrigendum to "Borderline ovarian tumors and low-grade serous carcinoma: A retrospective analysis from argentine and Uruguayan oncology centers" [Surg. Oncology 66 (2026) 102441].

Surgical oncology·2026
Same author

Topical resiquimod elicits systemic protection and improves anti-PD1 therapy in melanoma via priming of CD8+ T cells.

Cancer immunology research·2026
Same author

The Promotion Effect of Dust on Oxidative Potential of PM<sub>2.5</sub> via Photochemical Aging.

Environmental science & technology·2026
Same author

Open surgery in lambdoid-related plagiocephaly: detailed techniques, risks, and long-term results.

Child's nervous system : ChNS : official journal of the International Society for Pediatric Neurosurgery·2026

Related Experiment Video

Updated: May 21, 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

474

Optimizing generative AI by backpropagating language model feedback.

Mert Yuksekgonul1, Federico Bianchi2, Joseph Boen3

  • 1Department of Computer Science, Stanford University, Stanford, CA, USA. merty@stanford.edu.

Nature
|March 20, 2025
PubMed
Summary

TextGrad optimizes artificial intelligence (AI) systems by using large language models (LLMs) to provide feedback for automatic improvement. This framework accelerates AI development across various scientific and engineering applications.

More Related Videos

The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition
05:15

The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

10.7K
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

9.9K

Related Experiment Videos

Last Updated: May 21, 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

474
The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition
05:15

The Spatial Memory Game: Testing the Relationship Between Spatial Language, Object Knowledge, and Spatial Cognition

Published on: February 19, 2018

10.7K
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
09:27

Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language

Published on: October 13, 2018

9.9K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Science

Background:

  • AI systems increasingly rely on orchestrating multiple large language models (LLMs) and specialized tools.
  • Current AI system development is largely handcrafted and heuristically optimized, hindering rapid progress.
  • Automatic differentiation and backpropagation revolutionized neural network optimization, presenting an analogy for current AI challenges.

Purpose of the Study:

  • Introduce TextGrad, a novel framework for optimizing AI systems.
  • Enable automatic optimization of generative AI systems through LLM-generated feedback.
  • Demonstrate the versatility and effectiveness of TextGrad across diverse applications.

Main Methods:

  • TextGrad utilizes backpropagation of LLM-generated feedback to refine AI systems.
  • Natural language feedback is employed to critique and suggest improvements for prompts and outputs.
  • The framework supports optimization of various components within AI systems, including prompts and generated content.

Main Results:

  • TextGrad enables automatic optimization of generative AI systems for diverse tasks.
  • Demonstrated effectiveness in solving complex scientific problems at PhD level.
  • Successfully optimized radiotherapy treatment plans, molecule design, coding, and agentic systems.

Conclusions:

  • TextGrad offers a versatile framework for the automatic optimization of AI systems.
  • The approach leverages LLM feedback for significant improvements across scientific and engineering domains.
  • Empowers scientists and engineers to develop impactful generative AI applications more efficiently.