Hacker News Reader

Comment by gdcbe | Hacker News Reader

“Where we going we don’t need docs”. That scares me… docs are among other things there to provide context and info for things not clear from why certain choices were made or not made… no way your AI is going to guess that I put that restriction because of an explicit request from product, despite it looking wrong…

View on HN

Cofounder of Greptile here, good documentation is not going anywhere. What we do hate is going through bad documentation to find the tiny bit of information we need that is more often than not outdated to fit our needs. We are looking for ways to integrate information not explicitly written in code to understand codebases as well.

Indeed. Code describes how something is done, and possibly what is done, but it seldom fully describes why something is done, or why code exists in the first place.

The latter is typically the realm of requirements, design documentation, and possibly test plans.

Generating such documentation from code seems quite impossible, or at least wrong.

It is unfortunate that most open source software is lacking in such documentation, giving off bad signals to junior developers.

Edit: not to take away from the product being discussed here, which seems very useful! I am merely supporting the parent here.

This is a great point, and something we think about. I think to an extent a super smart version of our product could infer intent from the code but there would be definitely something amiss if the author's intent was just never available.

> The latter is typically the realm of requirements, design documentation, and possibly test plans.

You forgot one of the biggest spots for "why" documentation... git commit messages, where the point is to say why you made this change. Maybe taking into account the commit messages around the code in question would help.

"Initial commit" is my goto commit message.

Still a great idea, though. Ingesting all data from JIRA may be beneficial as well.

Yep... and the why of that message is apparent and makes perfect sense for the first commit. If you only ever start projects and never work on them again, that is all you need.

If you don't use proper commit messages you also probably don't have proper docs

We already do that and more at Maru.ai - reach out if you're interested.

Yep, agreed. As a founder of another YC company that's done a bunch of RAG on code and docs, the accuracy boost you get from having good docs makes a massive difference. You really do need a human interpreter to show you "how to use" a product.

This sort of tech will just spur developers to put proper comments in their code, which they should have been doing in the first place.

Didn't even think about that, hopefully it turns out to be true.

Could even make it an explicit feature, to consume jsdoc/javadoc/etc comments

I hope so! Unfortunately it will definitely be massively increasing the ratio of documentation to intentional documentation, so we'll have to see whether it increases documentation usability or not.

I can imagine the founder shout “Where we going we don’t need docs” whilst shoveling VC money into the steam engine.

Reply on news.ycombinator.com