From experiment and from real-world use, I’ve seen a number of things help reduce those risks and keep the “AI” on the rails.
• Working in smaller steps
• Testing after every step
• Reviewing code after every step
• Refactoring code as soon as problems appear
• Clarifying prompts with examples
— Jason Gorman, "Why Does Test-Driven Development Work So Well In 'AI'-assisted Programming?"
As software engineers we don’t just crank out code—in fact these days you could argue that’s what the LLMs are for. We need to deliver code that works—and we need to include proof that it works as well. Not doing that directly shifts the burden of the actual work to whoever is expected to review our code.
— Simon Willison, "Your job is to deliver code you have proven to work"