←back to thread

Open-source Zig book

(www.zigbook.net)
692 points rudedogg | 3 comments | 16 Nov 25 19:44 UTC | HN request time: 0.021s | source
Show context
rudedogg ◴[17 Nov 25 10:42 UTC] No.45952436[source]▶
I submitted this and unfortunately it is likely AI generated. The authors github history suggests it at the very least, along with seemingly misunderstanding a reference to a Zig language feature (labeled blocks - https://zig.guide/language-basics/labelled-blocks/) in the project issues (https://github.com/zigbook/zigbook/issues/4).

I’m not sure how much value is to be had here, and it’s unfortunate the author wasn’t honest about how it was created.

I wish I wouldn’t have submitted this so quickly but I was excited about the new resource and the chapters I dug into looked good and accurate.

I worry about whether this will be maintained, if there are hallucinations, and if it’s worth investing time into.

replies(13): >>45952561 #>>45952581 #>>45952667 #>>45952728 #>>45952742 #>>45952869 #>>45953014 #>>45953055 #>>45953161 #>>45953533 #>>45953660 #>>45956501 #>>45969184 #
1. Wowfunhappy ◴[17 Nov 25 11:06 UTC] No.45952561[source]▶
Are you sure? Right on https://www.zigbook.net/chapters/00__zigbook_introduction it says:

> The Zigbook intentionally contains no AI-generated content—it is hand-written, carefully curated, and continuously updated to reflect the latest language features and best practices.

The author could of course be lying. But why would you use AI and then very explicitly call out that you’re not using AI?

replies(2): >>45952613 #>>45952661 #
2. UpsideDownRide ◴[17 Nov 25 11:14 UTC] No.45952613[source]▶
Because AI content is at minimum controversial nowadays. And if you are ok with lying about authorship then It is not further down the pole to embelish the lie a bit more
3. rudedogg ◴[17 Nov 25 11:24 UTC] No.45952661[source]▶
> Are you sure?

There are too many things off about the origin and author to not be suspicious of it. I’m not sure what the motivation was, but it seems likely. I do think they used the Zig source code heavily, and put together a pipeline of some sort feeding relevant context into the LLM, or maybe just codex or w/e instructed to read in the source.

It seems like it had to take quite a bit of effort to make, and is interesting on its own. And I would trust it more if I knew how it was made (LLMs or not).

As another suspicious data point see this issue by the author: https://github.com/microsoft/vscode/issues/272725

Edit: https://news.ycombinator.com/item?id=45952581 found some concrete issues