Hacker News Reader

Comment by yodon | Hacker News Reader

> We study a common intermediate setting: a developer pastes one complete file into a chat assistant [5], which sees the file’s internal structure but not its callers or dependencies.

Ack! Do people actually try to develop software this way?

View on HN

Not any more, but it was common before Claude Code came along (~18 months ago). Based on the model versions used it may have still been the most common thing when the paper was started.

It's pretty much the standard way to develop in OOP.

You are not supposed to hold all of the code in context, but to have a single object and reason about with what it see.s

When I need modification to a small independent Python script (<1000 loc), sure.

Not for anything serious though.

Non-technical people often have no clue that there are options

I do it from time to time when I’ve run out of tokens at the end of the month. But even then I’ve created a script to pack multiple code files and their dependencies into a single txt, with a tree overview.

And of course you never change the test suite in the process… That would be bad developer practice, LLM or not.

Gemini 3.1 Pro can easily work with this effectively, if not a bit slower than an agent.

> But even then I’ve created a script to pack multiple code files and their dependencies into a single txt, with a tree overview.

Like:

    $ cat $(find project/ -name '*.py' -type f)

?

No, they test what LLM are capable of this way. They then examine the results by reading the code and reasoning about the changes the LLM made, rather than just throwing up their arms and going "Ack!" as if that's anything.

Reply on news.ycombinator.com