Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Using LLM is perfect for writing documentation which is something I always had problems with it.


As someone who has dealt with projects with AI-generated documentation... I can't really say I agree. Good documentation is terse, efficiently communicating the essential details. AI output is soooooooo damn verbose. What should've been a paragraph becomes a giant markdown file. I like reading human-written documentation, but AI-slop documentation is so tedious I just bounce right off.

Plus, when someone wrote the documentation, I can ask the author about details and they'll probably know since they had enough domain expertise and knowledge of the code to explain anything that might be missing. I can't trust you to know anything about the code you had an AI generate and then had an AI write documentation for.

Then there's the accuracy issue. Any documentation can always be inaccurate and it can obviously get outdated with time, but at least with human-authored documentation, I can be confident that the content at some point matched a person's best understanding of the topic. With AI, no understanding is involved; it's just probabilistically generated text, we've all hopefully seen LLMs generate plausible-sounding but completely wrong text enough to somewhat doubt their output.


Classic perfect/good.

The choice is not usually “have humans write amazing top notch documentation, or use an LLM”.

The choice is usually “have sparse, incomplete, out-of-date documentation… or use an LLM”.


And my claim is that the latter is better.


Cool, so just ignore documentation then. Problem solved for everyone.


I dont see how that solves anything.


* Projects can focus on code first, and do best-effort on docs for low cost * Most of us get reasonable quality documentation, much better than what some poor developer would turn out in spare moments * You are spared from the outrage of imperfect documentation


We wouldn't have these silly arguments?


Gah hopefully the meaning was clear from context, but I just realized I said "latter" when I meant "former". Inconsistent human documentation is better than miles upon miles of AI-slop documentation.


Given that people have access to LLMs themselves, publishing their output in lieu of good documentation (no matter how sparse) seems like it’s mostly downside.


Probabilistically generated text is light years better than my human generated mess. I know my limits and documentation is one of them.


This immediately invalidates a software or technical project for me. The value of documentation isn't the output alone, but the act of documenting it by a person or people that understand it.

I have done a lot of technical writing in my career, and documenting things is exactly where you run into the worst design problems before they go live.




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

Search: