Vibe coding

Evidence (4)

• 6Martin Fowler·7/21/2026research
  Thoughtworks Retreat Notes Highlight AI Coding Risks and Modernization

  Martin Fowler summarizes findings from Thoughtworks' Future of Software Development Retreat, where key themes included verification becoming more important than code generation, the rise of harness engineering, and an apprenticeship crisis in organizations. The post also warns that LLM-assisted vibe coding can create security, governance, and shadow IT risks, especially when executives overestimate productivity gains and underappreciate context and controls.

• 4Hacker News·7/14/2026research
  Why AI-assisted coding can break team coordination

  Armin Ronacher argues that AI-assisted programming can make individual developers far more productive, but may weaken the shared understanding that large software projects depend on. He compares this to the Tower of Babel: when local changes become easy to make without human coordination, the common language of architecture, boundaries, and invariants can erode even as code continues to ship.

• 4Martin Fowler·5/21/2026research
  Bliki: Vibe Coding

  Martin Fowler describes vibe coding as building software by prompting an LLM without inspecting the generated code, a method suited to disposable prototypes and limited-use tools. He warns that this approach can create maintainability, correctness, and security risks, and distinguishes it from agentic programming, where developers still review and care about the code.

• 5Martin Fowler·3/4/2026research
  Rethinking Human and Agent Roles in Software Development Loops

  The article argues that software teams should focus humans on the outcome-driven “why loop” while letting agents handle more of the implementation-focused “how loop.” It describes software development as nested loops that create, select, and validate artifacts such as code, tests, tools, and documentation, and questions how much internal quality needs to be preserved when LLMs generate software.