Episode 43: Rewriting in the Age of AI

Jeffrey and Isaac discuss their stance on 'never rewriting' given the possibility of AI making rewriting faster, cheaper, and less risky. They explore the limitations of current AI capabilities and the potential benefits of AI-assisted refactoring. The conversation delves into the idea of using AI to write tests and improve code quality. They also discuss the challenges and opportunities of AI in language switching and high-performance code optimization. Overall, the episode highlights the evolving role of AI in the rewriting process and the potential impact it may have on software development in the future. Takeaways - AI is not yet ready for code rewriting, but it has the potential to assist in the process. - AI can be used to write tests and improve code quality, but human supervision is crucial for effective results. - AI can help understand code better when provided with business context and documentation. - AI may play a significant role in language switching and high-performance code optimization in the future. Chapters 00:00 Introduction 00:11 The Possibility of Rewriting with AI 01:23 AI Not Ready for Rewriting 03:11 Manual Attempt at Automated Refactoring 04:32 Automated Refactoring Pipeline 05:43 AI-Assisted Code Refactoring 06:12 Value of Human Supervision 07:10 Understanding Code with AI 09:35 Adding Business Context to Code 10:15 AI and Changing Development Processes 11:12 AI as a New Compiler 12:09 AI-Assisted Language Switching 13:38 AI and High-Performance Code 15:03 AI Improving Code Quality 18:30 AI and Language Switching 19:09 The Future of AI in Rewriting 20:21 Conclusion