Salta al contenido principal
Disciplinas »
2026
2025
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
AACCs/FFLCH
Pró-Reitoria de Pós-Graduação
Outros
Suporte »
Acesso
Perfis
Ouvintes
Docentes
Criação de Disciplinas da USP
Documentação
HelpDesk e Contato
Guia de uso
Sobre
Español - Internacional (es)
Deutsch (de)
English (en)
Español - Internacional (es)
Français (fr)
Italiano (it)
Português - Brasil (pt_br)
Buscar por todo el sitio
Buscar
Cerrar
Realizar búsqueda
Selector de búsqueda de entrada
Acessar
MAC5913 - Inteligência artificial generativa para engenharia de software (2025)
Página Principal
Cursos
2025
IME
MAC
MAC5913--2025
Análise (Reasoning) e atuação
Slides
Slides
Requisitos de finalización
Haga clic en
6-Reasoning-Acting.pdf
para ver el archivo.
◄ Paper: ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet? by Tamanna et al.
Saltar a actividad
Saltar a actividad
Avisos
Informações gerais
Repositório de notebooks
Discussões
Slides
Paper: Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond by Yang et al.
Tokenizador da OpenAI
Slides
Notebook: visualização
Notebook: fine-tuning para detecção de vulnerabilidades
Paper: Attention is all you need by Vaswani et al.
Slides
Paper: A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT by White et al.
Paper: ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design by White et al.
Paper: ReAct: Synergizing Reasoning and Acting in Language Models by Yao et al.
Slides
Paper: ThinkRepair: Self-Directed Automated Program Repair by Yin et al.
Paper: Test-Case-Driven Programming Understanding in Large Language Models for Better Code Generation by Tian et al.
Slides
Notebook: RAG para usar uma API
Paper: ChatGPT Inaccuracy Mitigation during Technical Report Understanding: Are We There Yet? by Tamanna et al.
Notebook: Function calling para obter informações do Git
Slides
Paper: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models by Mizardeh et al.
Paper: Role play with large language models by Shanahan et al.
Paper: DAnTE: A Taxonomy for the Automation Degree of Software Engineering Tasks by Melegati & Guerra
Projeto final
Avaliação pelos pares
Fotos e vídeos do curso
Todos os posters
Notebook: Function calling para obter informações do Git ►