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.
Related Insights
Overly structured, workflow-based systems that work with today's models will become bottlenecks tomorrow. Engineers must be prepared to shed abstractions and rebuild simpler, more general systems to capture the gains from exponentially improving models.
Don't just sprinkle AI features onto your existing product ('AI at the edge'). Transformative companies rethink workflows and shrink their old codebase, making the LLM a core part of the solution. This is about re-architecting the solution from the ground up, not just enhancing it.
Snyk founder's new venture, TESOL, posits that AI will make code disposable. Instead of code being the source of truth, a durable, versioned 'spec' document defining requirements will become the core asset. AI agents will generate the implementation, fundamentally changing software development.
High productivity isn't about using AI for everything. It's a disciplined workflow: breaking a task into sub-problems, using an LLM for high-leverage parts like scaffolding and tests, and reserving human focus for the core implementation. This avoids the sunk cost of forcing AI on unsuitable tasks.
Contrary to the classic engineering rule to "never rewrite," Block's CTO believes AI will make this the new standard. He is pushing his teams to imagine a world where for every release, they delete the entire app (`rm -rf`) and rebuild it from scratch, with AI respecting all incremental improvements from the previous version.
The role of a senior developer is evolving. They now focus on defining outcomes by writing tests that a piece of code must accomplish. The AI then generates the actual implementation, allowing small teams to build complex systems in a fraction of the traditional time.
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 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.
As AI generates more code, the core engineering task evolves from writing to reviewing. Developers will spend significantly more time evaluating AI-generated code for correctness, style, and reliability, fundamentally changing daily workflows and skill requirements.
Historically, developer tools adapted to a company's codebase. The productivity gains from AI agents are so significant that the dynamic has flipped: for the first time, companies are proactively changing their code, logging, and tooling to be more 'agent-friendly,' rather than the other way around.