I am just impressed by the quality and details and approach of it all.
Nicely done (PS: I know nothing about systems programming and I have been writing code for 25 years)
I am just impressed by the quality and details and approach of it all.
Nicely done (PS: I know nothing about systems programming and I have been writing code for 25 years)
Because AI gets things wrong, often, in ways that can be very difficult to catch. By their very nature LLMs write text that sounds plausible enough to bypass manual review (see https://daniel.haxx.se/blog/2025/07/14/death-by-a-thousand-s...), so some find it best to avoid using it at all when writing documentation.
A calculator exists solely for the realm of mathematics, where you can afford to more or less throw away the value of human input and overall craftsmanship.
That is not the case with something like this, which - while it leans in to engineering - is in effect viewed as a work of art by people who give a shit about the actual craft of writing software.
Quality prose usually only becomes that after many reviews.
If it was so obviously written by AI then finding those mistakes should be easy?
Passing even correct information through an LLM may or may not taint it; it may create sentences which on first glance are similar, but may have different, imprecise meaning - specific wording may be crucial in some cases. So if the style is under question, the content is as well. And if you can write the technically correct text at first, why would you put it through another step?
> 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.
If the site would have said something like "We use AI to clean up our prose, but it was all audited thoroughly by a human after", I wouldn't have an issue. Even better if they shared their prompts.
No it isn't. My TI-83 is deterministic and will give me exactly what I ask for, and will always do so, and when someone uses it they need to understand the math first or otherwise the calculator is useless.
These AI models on the other hand don't care about correctness, by design don't give you deterministic answers, and the person asking the question might as well be a monkey as far as their own understanding of the subject matter goes. These models are if anything an anti-calculator.
As Dijkstra points out in his fantastic essay on the idiocy of natural language "computation", what you are doing is exactly not computation but a kind of medieval incantation. Computers were designed to render impossible precisely the nonsense that LLMs produce. The biggest idiot on earth will still get a correct result from the calculator because unlike the LLM it is based on boolean logic, not verbal or pictorial garbage.
https://www.cs.utexas.edu/~EWD/transcriptions/EWD06xx/EWD667...
“The Party told you to reject the evidence of your eyes and ears. It was their final, most essential command.”But if you carefully review and iterate the contributions of your writers - human or otherwise - you get a quality outcome.
But why would you trust the author to have done that when they are lying in a very obvious way about not using AI?
Using AI is fine, it's a tool, it's not bad per se. But claiming very loud you didn't use that tool when it's obvious you did is very off-putting.
But why would a serious person claim that they wrote this without AI when it's obvious they used it?!
Using any tool is fine, but someone bragging about not having used a tool they actually used should make you suspicious about the amount of care that went to their work.
I am just a human supremacist.
I suppose the author may have deliberately added the "No AI assistance" notice - making sure all the hallucinated bugs are found via outraged developers raising tickets. Without that people may not even have bothered.
Agree. What matters is quality, regardless of what/who made it.
O.t.o.h., it is funny to see tech people here, that work on implementing technology, taking an approach so... Luddite and "anti-tech".
i think 90% of the comments were about the AI part rather than the actual product - which seems very cool and definitely took a lot of effort to put together.