The highest quality codebase

Am I the only one that is surprised that the app still works?!

> There's a significant blind-spot in current LLMs related to blue-sky thinking and creative problem solving. It can do structured problems very well, and it can transform unstructured data very well, but it can't deal with unstructured problems very well.

While this is true in my experience, the opposite is not true. LLMs are very good at helping me go through a structure processing of thinking about architectural and structural design and then help build a corresponding specification.

More specifically the "idea honing" part of this proposed process works REALLY well: https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/

This: Each question should build on my previous answers, and our end goal is to have a detailed specification I can hand off to a developer. Let’s do this iteratively and dig into every relevant detail. Remember, only one question at a time.

LLMs have this strong bias towards generating code, because writing code is the default behavior from pre-training.

Removing code, renaming files, condensing, and other edits is mostly a post-training stuff, supervised learning behavior. You have armies of developers across the world making 17 to 35 dollars an hour solving tasks step by step which are then basically used to generate prompt/responses pairs of desired behavior for a lot of common development situations, adding desired output for things like tool calling, which is needed for things like deleting code.

A typical human working on post-training dataset generation task would involve a scenario like: given this Dockerfile for a python application, when we try to run pytest it fails with exception foo not found. The human will notice that package foo is not installed, change the requirements.txt file and write this down, then he will try pip install, and notice that the foo package requires a certain native library to be installed. The final output of this will be a response with the appropriate tool calls in a structured format.

Given that the amount of unsupervised learning is way bigger than the amount spent on fine-tuning for most models, it is not surprise that given any ambiguous situation, the model will default to what it knows best.

More post-training will usually improve this, but the quality of the human generated dataset probably will be the upper bound of the output quality, not to mention the risk of overfitting if the foundation model labs embrace SFT too enthusiastically.

This reflects my experience with human programmers. So many devs are taught to add layers of complexity in pursuit of "best practices". I think the LLM was trained to behave this way.

In my experience, Claude can actually clean up a repo rather nicely if you ask it to (1) shrink source code size (LOC or total bytes), (2) reduce dependencies, and (3) maintain integration tests.

But anyone didn't do it... you an expert in software development did it.

I would hazard a guess that your knowledge lead to better prompts, better approach... heck even understanding how to build a status bar menu on Mac OS is slightly expert knowledge.

You are illustrating the GP's point, not negating it.