AI for mass-scale code refactoring and analysis

• Verfasst von: Gehring, Justine [VerfasserIn]
• Verfasst von: Kundzich, Olga [VerfasserIn]
• Verfasst von: Johnson, Pat [VerfasserIn]
• Titel: AI for mass-scale code refactoring and analysis
• Titelzusatz: how to make AI more efficient, cost-effective, and accurate at scale
• Verf.angabe: Justine Gehring, Olga Kundzich, and Pat Johnson
• Ausgabe: First edition.
• Verlagsort: Sebastopol, CA
• Verlag: O'Reilly Media, Inc.
• Jahr: 2024
• Umfang: 1 online resource (42 pages)
• Illustrationen: illustrations
• Fussnoten: Includes bibliographical references
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Logiciels ; Refactorisation
• Sach-SW: Intelligence artificielle
• Sach-SW: Apprentissage automatique
• Sach-SW: artificial intelligence
• K10plus-PPN: 1903889979
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext
• Lokale URL UB: Bibliothek der Medizinischen Fakultät Mannheim der Universität Heidelberg
• Bibliothek/Idn: UW / m4585341110
• Lokale URL Inst.: Zum Volltext

Abstract

As the software development landscape evolves, the challenge of managing and refactoring extensive code bases becomes increasingly complex. AI methods of code refactoring, while effective for smaller scales, can falter under the weight of mass-scale operations. The need for efficiency, accuracy, and consistency is more critical than ever. This key report provides an in-depth exploration of how to optimize AI for these extensive tasks to minimize the need for "human in the loop." Discover how AI can transform the daunting job of mass-scale code refactoring into a streamlined, trustworthy process.