Hacker News Reader

> I find that it is IMPORTANT to never start these coding sessions with "write X code". Instead, begin with a "open plan"

Most llms that I use nowadays usually make a plan first on their own by default without need to be especially prompted. This was definitely not the case a year ago or so. I assume new llms have been trained accordingly in the meantime.

View on HN

True. And that is a step forward. I notice that they make the plan, and THEN write the code in the same forward pass/generation sequence. The challenge here is that all of the incorrect assumptions get "lumped" into this pass and can pollute the rest of the interaction.

The initial interaction also sets the "scene" for other things, like letting the LLM know that there might be other dependencies and it should not assume behavior (common for most realistic software tasks).

An example prompt I have used (not by any means perfect) ...

> I need help refactoring some code. Please pay full attention. Think deeply and confirm with me before you make any changes. We might be working with code/libs where the API has changed so be mindful of that. If there is any file you need to inspect to get a better sense, let me know. As a rule, do not write code. Plan, reason and confirm first.

--- I refactored my db manager class, how should I refactor my tests to fit the changes?

Reply on news.ycombinator.com