Beyond code generation, Patrick Collison sees a huge opportunity for AI in automated refactoring. He imagines an AI that continuously improves a codebase's architecture, turning the 'detritus' from rapid development into elegant, maintainable systems, thus solving the classic speed-versus-quality tradeoff.

The focus of "code review" is shifting from line-by-line checks to validating an AI's initial architectural plan. After plan approval, AI agents like OpenAI's Codex can effectively review their own generated code, a capability they have been explicitly trained for, making human code review obsolete.

As AI agents handle the mechanics of code generation, the primary role of a developer is elevated. The new bottlenecks are not typing speed or syntax, but higher-level cognitive tasks: deciding what to build, designing system architecture, and curating the AI's work.

AI tools are automating code generation, reducing the time developers spend writing it. Consequently, the primary skill shifts to carefully reviewing and verifying the AI-generated code for correctness and security. This means a developer's time is now spent more on review and architecture than on implementation.

Many software development conventions, like 'clean code' rules, are unproven beliefs, not empirical facts. AI interacts with code differently, so engineers must have the humility to question these foundational principles, as what's 'good code' for an LLM may differ from what's good for a human.

The long-held rule by Joel Spolsky to "never rewrite your code" no longer applies in the AI era. For an increasing number of scenarios, it is more efficient to have an LLM regenerate an entire system, like a unit test suite, from scratch than to attempt to incrementally fix or refactor it.

While AI coding assistants appear to boost output, they introduce a "rework tax." A Stanford study found AI-generated code leads to significant downstream refactoring. A team might ship 40% more code, but if half of that increase is just fixing last week's AI-generated "slop," the real productivity gain is much lower than headlines suggest.

Instead of fearing AI, design engineers should leverage it to automate boilerplate and foundational code. This frees up mental energy and time to focus on what truly matters: crafting the nuanced, high-quality interactions and animations that differentiate a product and require human creativity.

Instead of fighting for perfect code upfront, accept that AI assistants can generate verbose code. Build a dedicated "refactoring" phase into your process, using AI with specific rules to clean up and restructure the initial output. This allows you to actively manage technical debt created by AI-powered speed.