Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Kohlberg's Theory of Moral Development01:19

Kohlberg's Theory of Moral Development

1.1K
Kohlberg's theory of moral development uses the Heinz dilemma — a thought experiment in which a man, Heinz, must decide whether to steal an unaffordable drug to save his dying wife — to illustrate the evolution of moral reasoning. This framework, divided into three levels with two stages, highlights how individuals' understanding of right and wrong becomes increasingly complex.
Pre-Conventional Level
At the pre-conventional level, morality is primarily driven by personal...
1.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

3.7K
3.7K
Improving Translational Accuracy02:07

Improving Translational Accuracy

15.2K
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...
15.2K
Stereotype Content Model02:16

Stereotype Content Model

15.5K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.5K
Self-Evaluation Maintenance Model01:29

Self-Evaluation Maintenance Model

343
The Self-Evaluation Maintenance (SEM) model offers a psychological framework to understand how individuals’ self-esteem is influenced by the achievements of others, particularly those with whom they share close personal bonds. The SEM model operates when personal rather than social identity guides individuals. Central to this model is the notion that individuals have an inherent desire to preserve a favorable self-image, which is continuously shaped by interpersonal comparisons and...
343
Language Development01:22

Language Development

973
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...
973

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Agreements and disagreements with resource-rational contractualism.

The Behavioral and brain sciences·2026
Same author

Fair contracts for artificial intelligence?

The Behavioral and brain sciences·2026
Same author

Technological <i>folie à deux</i>: feedback loops between AI chatbots and mental health.

Nature. Mental health·2026
Same author

Imagining and building wise machines: the centrality of AI metacognition.

Trends in cognitive sciences·2026
Same author

The utility of early gestational OGTT and biomarkers for the development of gestational diabetes mellitus: an international prospective multicentre cohort study.

Diabetologia·2025
Same author

We need a new ethics for a world of AI agents.

Nature·2025
Same journal

Retraction Note: NSD2 targeting reverses plasticity and drug resistance in prostate cancer.

Nature·2026
Same journal

Enhanced B cell priming induces broadly neutralizing HIV-1 apex antibodies.

Nature·2026
Same journal

Vaccination elicits HIV broadly neutralizing antibodies in primates.

Nature·2026
Same journal

Child online safety needs more than social-media bans.

Nature·2026
Same journal

Ebola preparedness must start with ecosystems and before humans show symptoms.

Nature·2026
Same journal

AI tools can speed up thinking, but evidence still comes from the lab bench.

Nature·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Feb 20, 2026

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

1.2K

Una hoja de ruta para evaluar la competencia moral en modelos de lenguaje grandes

Julia Haas1, Sophie Bridgers2, Arianna Manzini2

  • 1Google DeepMind, London, UK. juliahaas@google.com.

Nature
|February 18, 2026
PubMed
Resumen
Este resumen es generado por máquina.

Evaluar la competencia moral de los modelos de lenguaje grandes (LLM) es crucial para su despliegue seguro. Se necesitan nuevos métodos de evaluación para abordar desafíos como la imitación y la complejidad en la ética de la IA.

Palabras clave:
ética de la IAcompetencia moralmodelos de lenguaje grandesevaluación de IAdespliegue responsable de IA

Más Videos Relacionados

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

1.6K

Videos de Experimentos Relacionados

Last Updated: Feb 20, 2026

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

1.2K
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

1.6K

Área de la Ciencia:

  • Ética de la Inteligencia Artificial
  • Moralidad Computacional
  • Seguridad de la IA

Sus antecedentes:

  • Los LLM se utilizan cada vez más en roles sensibles, lo que requiere una comprensión de sus capacidades morales.
  • Las evaluaciones actuales se centran en el desempeño moral (adecuación de la salida) en lugar de la competencia moral (razonamiento basado en consideraciones morales).
  • La evaluación de la competencia moral es vital para predecir el comportamiento de la IA, generar confianza y justificar atribuciones morales.

Objetivo del estudio:

  • Ir más allá de la evaluación del desempeño moral para evaluar la competencia moral de los LLM.
  • Identificar y abordar los desafíos fundamentales en la evaluación de la competencia moral de los LLM.
  • Proponer una hoja de ruta para la evaluación científicamente fundamentada de la competencia moral de la IA.

Principales métodos:

  • Identificación de desafíos clave: el problema de la imitación (imitación vs. comprensión), la multidimensionalidad moral (factores sensibles al contexto) y el pluralismo moral (estándares globales de IA).
  • Defensa de un conjunto de evaluaciones contradictorias y confirmatorias.
  • Desarrollo de un marco para evaluar la competencia moral de la IA.

Principales resultados:

  • La evaluación de la competencia moral de los LLM enfrenta obstáculos significativos debido a la arquitectura del modelo y la complejidad moral.
  • Se identifican el problema de la imitación, la multidimensionalidad moral y el pluralismo moral como desafíos críticos.
  • Se propone un enfoque de evaluación estructurado para evaluar científicamente la competencia moral de los LLM.

Conclusiones:

  • Una comprensión científica sólida de la competencia moral de los LLM requiere abordar los desafíos identificados.
  • La atribución responsable de competencia moral a los LLM requiere una evaluación rigurosa y científicamente fundamentada.
  • El desarrollo y despliegue futuros de la IA deben priorizar la evaluación ética de las capacidades morales de la IA.