Assigning AI: Seven Approaches for Students, with Prompts

Texto completo

This paper examines the transformative role of Large Language Models (LLMs) in education and their potential as learning tools, despite their inherent risks and limitations. The authors propose seven approaches for utilizing AI in classrooms: AI-tutor, AI-coach, AI-mentor, AI-teammate, AI-tool, AI-simulator, and AI-student, each with distinct pedagogical benefits and risks. The aim is to help students learn with and about AI, with practical strategies designed to mitigate risks such as complacency about the AI's output, errors, and biases. These strategies promote active oversight, critical assessment of AI outputs, and complementation of AI's capabilities with the students' unique insights. By challenging students to remain the "human in the loop", the authors aim to enhance learning outcomes while ensuring that AI serves as a supportive tool rather than a replacement. The proposed framework offers a guide for educators navigating the integration of AI-assisted learning in classrooms.

Para cada uno de los siete usos —IA como mentor (feedback), tutor (instrucción directa), coach (metacognición: reflexión y premortem), compañero de equipo (estructura del equipo y abogado del diablo), estudiante (aprender enseñando), simulador (práctica mediante juego de rol) y herramienta— el artículo expone la base teórica, ofrece un prompt de ejemplo con muestras de la interacción, analiza los riesgos (confabulación, sesgos, privacidad, dependencia), da pautas para el profesorado e instrucciones para el alumnado, y explica cómo construir un prompt propio. Un apéndice recoge con qué modelos (GPT-4, GPT-3.5, Bing en modo creativo, Claude y Bard) funcionaba cada prompt en junio de 2023.