Source URL: https://developers.slashdot.org/story/25/06/04/1233253/morgan-stanley-says-its-ai-tool-processed-9-million-lines-of-legacy-code-this-year-and-saved-280000-developer-hours?utm_source=rss1.0mainlinkanon&utm_medium=feed
Source: Slashdot
Title: Morgan Stanley Says Its AI Tool Processed 9 Million Lines of Legacy Code This Year And Saved 280,000 Developer Hours
Feedly Summary:
AI Summary and Description: Yes
Summary: Morgan Stanley’s deployment of its in-house AI tool, DevGen.AI, exemplifies significant advancements in the modernization of legacy code, especially within financial services. The utilization of AI not only enhances developer efficiency but also addresses security concerns related to outdated programming languages.
Detailed Description:
Morgan Stanley has introduced an innovative AI tool named DevGen.AI, designed to tackle a critical challenge in enterprise software—modernizing legacy code. This initiative has significant implications for security and compliance in software development, particularly within regulated industries like banking and finance. Here are the major points:
– **Tool Overview**: DevGen.AI has reviewed over nine million lines of legacy code, translating outdated programming languages into modern specifications efficiently.
– **Time Savings**: The tool has reportedly saved the developers approximately 280,000 hours, highlighting the efficiency gains that AI can provide in software development processes.
– **Technology Utilized**: Built on OpenAI’s GPT models, the tool leverages advanced AI techniques to facilitate the transition from old to new programming languages.
– **Pain Points**: The lack of expertise in older programming languages, such as Cobol, has been identified as a significant barrier that affects security and the adoption of new technology. This tool directly addresses that issue.
– **Proprietary Training**: By training the AI on its proprietary codebase, Morgan Stanley ensures that the tool is specifically aligned with the company’s unique programming needs, enhancing its functionality and effectiveness.
– **Accessibility for Developers**: The English specifications generated by DevGen.AI enable approximately 15,000 developers at Morgan Stanley to rewrite legacy code without needing specialized knowledge in antiquated languages.
This deployment not only demonstrates the practical applications of AI in automating and enhancing software development but also emphasizes the critical intersection of technology and security. By modernizing legacy systems, organizations can mitigate potential security vulnerabilities that arise from using outdated codebases, allowing for greater efficiency and compliance in their operations. Additionally, the capability to map legacy functions into understandable formats can bolster governance and oversight within software development processes.
Overall, DevGen.AI represents a novel approach to bridging the gap between legacy systems and modern programming practices, offering valuable insights for security and compliance professionals seeking to leverage AI within their domains.