2. Count on to iterate
As I discussed earlier than, the extra specific and chronic your directions are, the extra possible you’ll get one thing resembling your intentions. That mentioned, it’s unlikely you’ll get precisely what you need on the primary, second, third, and even fourth attempt—not even for any single facet of your program, not to mention the entire thing. Thoughts studying, not to mention precisely, continues to be fairly a method off. (Fortunately.)
A certain quantity of back-and-forth to get to what you need appears inevitable, particularly in case you are re-implementing a mission in a special language. The profit is you’re pressured to confront every set of adjustments as you go alongside, and ensure they work. The draw back is the method may be exhausting, and never in the identical method making iterative adjustments by yourself can be. Whenever you make your personal adjustments, it’s you versus the pc. When the agent is making adjustments for you, it’s you versus the agent versus the pc. The determinism of the pc by itself is changed by the indeterminism of the agent.
3. Take full accountability for the outcomes
My closing takeaway is to be ready to take accountability for each generated line of code within the mission. You can not resolve that simply because the code runs, it’s okay. In my case, Claude might have been the agent that generated the code, however I used to be there saying sure to it and signing off on selections at each step. Because the developer, you’re nonetheless accountable—and never only for ensuring all the things works. It issues how effectively the outcomes make the most of the goal language’s metaphors, ecosystem, and idioms.
