[bigblind]

> On projects where I have no understanding of the underlying technology (e.g. mobile apps), the code still quickly becomes a mess of bad choices. However, on projects where I know the technologies used well (e.g. backend apps, though not necessarily in Python), this hasn’t happened yet, even at tens of thousands of SLoC. Most of that must be because the models are getting better, but I think that a lot of it is also because I’ve improved my way of working with the models.

I wonder whether at some point we'll get a translation model, that translates relatively vague requests into sound architectural decisions, with some embedded knowledge of the environment you're building in, and that can ask clarifying questions when there are multiple options with different tradeoffs.

[mlnj]

Is that not already possible with Markdown spec files and planning mode?

[bigblind]

I guess? At least there you can review the plan, but is this planning mode any better at making architectural decisions than when you prompt an LLM and let it make the changes directly? (it might be, just not sure.)