News for hackers. Stuff that matters.
Re:LLMs are steroids for your Dunning-Kruger by gowld on Monday November 10, 2025 @02:00PM (#45879472)
Both comments are missing the reason that an encyclopedia should not be cited:

An encyclopedia does not cite its sources, and does not claim to be a primary source, its potentialymistakes cannot be checked.

(Wikipedia has the additional problem that, by default, the version cited is the ever-changing "latest" version, not a fixed and identified version.)

Re:LLMs are steroids for your Dunning-Kruger by miningape on Monday November 10, 2025 @02:07PM (#45879557)
You gave some good context I missed - The (even) more technical (read: pretentious) explanation is that it's a tertiary source. As a general rule of thumb secondary sources are preferred over primary sources, but both are acceptable in the right academic context.

I do understand the "latest version" argument, and it is a weakness, but it's also a double edged sword - it means Wikipedia can also be more up-to-date than (almost) any other source for the information. Thats why I say there's "nothing specifically wrong about Wikipedia either" it can be held in similar regard to other tertiary sources and encyclopaedias - with all the problems that come with those.

Re:LLMs are steroids for your Dunning-Kruger by jjk166 on Monday November 10, 2025 @03:05PM (#45880265)
That's not at all the reason.

Encyclopedias are tertiary sources, compilations of information generated by others. They are neither sources of first hand information (primary sources) nor original analysis (secondary sources). You can't cite encyclopedias because there's nothing to cite. The encyclopedia was not the first place the claim was made, even if it was the first place you happened to read it. You don't attribute a Wayne Gretsky quote to Michael Scott no matter how clearly he told you Wayne Gretsky said it.

Re:LLMs are steroids for your Dunning-Kruger by versteegen on Monday November 10, 2025 @07:23PM (#45882675)
What about scholarly encyclopedias? For example, the Stanford Encyclopedia of Philosophy. The articles are written in the style of a survey article, and if they're merely tertiary, I can't tell. If the intention behind a citation is a reference for a concept (an "existence proof" of it) rather than identifying its source or providing evidence, then a tertiary source such as to a textbook seems adequate.
Re:LLMs are steroids for your Dunning-Kruger by jjk166 on Monday November 10, 2025 @09:00PM (#45883273)
There is some nuance. Wikipedia is a tertiary source for the subjects of its articles. However, it is a primary source for what is on wikipedia. You can cite an encyclopedia the same way you would cite the dictionary (which is also a tertiary source) as a way of establishing that information is in circulation.

Likewise, primary sources for some claims may be tertiary sources for others. If you read the memoirs of a soldier in WW1 who is comparing his exploits to those of a roman general from antiquity, he is a primary source for the WW1 history and a tertiary source for the roman history.

Survey articles and textbooks are generally tertiary. They may include analysis which is secondary and citable, but even then only the parts which are original are citable.

As a more general rule, you can't cite a piece of information from a work which is itself citing that piece of information (or ought to be).

Re:LLMs are steroids for your Dunning-Kruger by smw on Monday November 10, 2025 @02:38PM (#45879939)
Maybe you haven't used Wikipedia? It very definitely cites its sources. Material that doesn't have a cited source is removed regularly.
Re:LLMs are steroids for your Dunning-Kruger by throwaway198846 on Monday November 10, 2025 @04:06PM (#45880934)
There is plenty of not properly sourced claims on Wikipedia
Re:LLMs are steroids for your Dunning-Kruger by mzajc on Tuesday November 11, 2025 @07:28AM (#45886521)
> (Wikipedia has the additional problem that, by default, the version cited is the ever-changing "latest" version, not a fixed and identified version.)

Only citing means copying the URL directly. If you use Wikipedia's "Cite this page" or an external reference management tool (e.g. Zotero), the current page ID will be appended to the URL.