Hacker Newsnew | past | comments | ask | show | jobs | submit | jv22222's commentslogin

I used Claude to document, in great detail, a 500k-line codebase in about an hour of well-directed prompts. Just fully explained it, how it all worked, how to get started working on it locally, the nuance of the old code, pathways, deployments using salt-stack to AWS, etc.

I don't think the moat of "future developers won't understand the codebase" exists anymore.

This works well for devs who write their codebase using React, etc., and also the ones rolling their own JavaScript (of which I personally prefer).


To make a parallel to actual human language: you can understand well a foreign language and not be able to speak it at the same level.

I found myself in that situation with both foreign languages and with programming languages / frameworks - understanding is much easier than creating something good. You can of course revert to a poorer vocabulary / simpler constructions (in both cases), but an "expert" speaker/writer will get a better result. For many cases the delta can be ignored, for some cases it matters.


How did you vet the quality of the documentation? I have no doubt that an LLM could produce a great deal of plausible-sounding documentation in short order. Even assuming you’re already completely familiar with the code base, reading through that documentation and fact checking it would take a great deal of effort.

What’s the quality like? I’d expect it to be riddled with subtly wrong explanations. Is Claude really that much better than older models (eg. GPT-4)?

Edit: Oops, just saw your other comment saying you’d verified it manually.


> I used Claude to document, in great detail, a 500k-line codebase in about an hour of well-directed prompts

Yes, but have you fully verified that the documentation generated matches the code? This is like me saying I used Claude to generate a year long workout plan. And that is lovely. But the generated thing needs to match what you wanted it for. And for that, you need verification. For all you know, half of your document is not only nonsense but it is not obvious that it's nonsense until you run the relevant code and see the mismatch.


Yes, since I spent over 10 years writing it in the first place it was easy to verify!

This is a key piece of information you left out of your original post.

Hey, I also sent this to feedback@nugget.one, but just in case it doesn't arrive:

I wasn't able to get into your 'startup ideas' site.

Signing in with google led to internal server error, and signing in with a password, I never received the verification email.

Thought I would let you know. Can't wait to get those sweet startup ideas....!


Thanks, I've been very focused on lightwave and as a result let that one slide a bit. I'll try to get it working in next week or so.

This - I even ran Claude to produce a security eval of openclaw for fun and it was mostly spot on - https://sriku.org/files/openclaw-secreport-claude-13feb2026....

If your project is on Github, you can also use https://deepwiki.com/. I have used it to get an overview of a new codebase quickly.

I'll get you a better mobile expereince by then.

It's related to keyboard layout. I've got a linux/windows keyboard coming in the mail. Will get it fixed. (it works with option+shift on osx)

will look into ctrl backspace to delete words like that idea


Added, now works.

The billion dollar homepage.

> Shift + Home/End for selecting text doesn't work > Ctrl + N for a new page doesn't work

One thing that's weird is that things like that are so easy for me to implement it's just sugar on top. Honestly I would just love to have a few folks tinkering with it saying hey it needs these few things. Just hard for one dev to think of all the things!


Thanks so much for your feedback, much appreciated.

Oh wow, thanks so much! Let me know how it goes, happy to tweak any annoyances.

Thanks! Yeah I liked the slash menu pattern from the block editors, just wanted it to take up less visual space that's why only a small popup with icons.

Thanks! No hard limit on team size. On the collab side, I load tested it with 210 people typing simultaneously in the same doc and it handled it fine (9ms median latency, zero dropped keystrokes). So a normal team won't come close to stressing it.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: