The productivity trap: Meet the perils and promises of AI-assisted coding

As AI accelerates the pace of coding, organizations will have a hard time keeping up; acceleration isn't useful if it's driving our projects straight into a brick wall of technical debt. This presentation explores the consequences of AI-assisted coding, weighing its potential to improve productivity against the risks of deteriorating code quality.

Adam delivers a fact-based examination of the short and long-term implications of using AI assistants in software development. Drawing from extensive research analyzing over 100,000 AI-driven refactorings in real-world codebases, we scrutinize the claims made by contemporary AI tools, demonstrating that increased coding speed does not necessarily equate to true productivity. Additionally, we also look at the correctness of AI generated code, a concern for many organizations today due to the error-prone nature of current AI tools.

Finally, the talk offers strategies for succeeding with AI-assisted coding. This includes introducing a set of automated guardrails that act as feedback loops, ensuring your codebase remains maintainable even after adopting AI-assisted coding.

Key insights include:

Novel Quality Metrics: Introduction and application of innovative metrics designed to act as guardrails, ensuring that AI contributions maintain high standards of code quality.
Balancing Speed and Quality: Strategies to leverage AI for increased efficiency while avoiding the pitfalls of technical debt.
Real-World Data: Fact-based presentation from comprehensive research on real-world codebases.