Local LLMs versus offline Wikipedia • Hacker News Board

Re: Local LLMs versus offline Wikipedia

#31

Post by bigyabai » Sat, Jul 19, 2025, 10:12 PM UTC

progval wrote: post #9

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

An unreliable computer treated as a god by a pre-information-age society sounds like a Star Trek episode.

Or the plot to 2001 if you managed to stay awake long enough.

Re: Local LLMs versus offline Wikipedia

#32

Post by ianmcgowan » Sat, Jul 19, 2025, 10:13 PM UTC

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

A tangent - sounds like https://en.wikipedia.org/wiki/The_Book_of_Koli - a key plot component is a chatty Sony AI music player. A little YA, but a fun read..

Re: Local LLMs versus offline Wikipedia

#33

Post by gretch » Sat, Jul 19, 2025, 10:14 PM UTC

progval wrote: post #9

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

An unreliable computer treated as a god by a pre-information-age society sounds like a Star Trek episode.

Definitely sounds like a plausible and fun episode.

On the other hand, real history if filled with all sorts of things being treated as a god that were much worse than "unreliable computer". For example, a lot of times it's just a human with malice.

So how bad could it really get

Re: Local LLMs versus offline Wikipedia

#34

Post by Philpax » Sat, Jul 19, 2025, 10:21 PM UTC

wangg wrote: post #25

Wouldn’t Wikipedia compress a lot more than llms? Are these uncompressed sizes?

Yes, they're uncompressed. For reference, `enwiki-20250620-pages-articles-multistream.xml.bz2` is 25,176,364,573 bytes; you could get that lower with better compression. You can do partial reads from multistream bz2, though, which is handy.

Re: Local LLMs versus offline Wikipedia

#35

Post by gonzobonzo » Sat, Jul 19, 2025, 10:23 PM UTC

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

Indeed. Ideally, you don't want to trust other people's summaries of sources, but you want to look at the sources yourself, often with a critical eye. This is one of the things that everyone gets taught in school, everyone's says they agree with, and then just about no one does (and at times, people will outright disparage the idea). Once out of school, tertiary sources get treated as if they're completely reliable.

I've found using LLM's to be a good way of getting an idea of where the current historiography of a topic stands, and which sources I should dive into. Conversely, I've been disappointed by the number of Wikipedia editors who become outright hostile when you say that Wikipedia is unreliable and that people often need to dive into the sources to get a better understanding of things. There have been some Wikipedia articles I've come across that have been so unreliable that people who didn't look at other sources would have been greatly mislead.

Re: Local LLMs versus offline Wikipedia

#36

Post by literalAardvark » Sat, Jul 19, 2025, 10:23 PM UTC

antonkar wrote: post #29

horseradish7k wrote: post #22

Earlier quoted context omitted.

we did that and still do. people just don't buy encyclopedias that much nowadays

Imagine taking the whole Web, removing spam, duplicates, bad explanations It will be the free new Wikipedia+ to learn anything in the best way possible, with the best graphs, interactive widgets, etc What LLMs have for free but humans for some reason don’t In some places it is possible to use copyrighted materials to educate if not directly for profit

Love it when Silicon Valley reinvents encyclopedias

Re: Local LLMs versus offline Wikipedia

#37

Post by anothermoron » Sat, Jul 19, 2025, 10:33 PM UTC

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

[dead]

Re: Local LLMs versus offline Wikipedia

#38

Post by GuB-42 » Sat, Jul 19, 2025, 10:36 PM UTC

wangg wrote: post #25

Wouldn’t Wikipedia compress a lot more than llms? Are these uncompressed sizes?

The downloads are (presumably) already compressed.

And there are strong ties between LLMs and compression. LLMs work by predicting the next token. The best compression algorithms work by predicting the next token and encoding the difference between the predicted token and the actual token in a space-efficient way. So in a sense, a LLM trained on Wikipedia is kind of a compressed version of Wikipedia.

Re: Local LLMs versus offline Wikipedia

#39

Post by ranger_danger » Sat, Jul 19, 2025, 10:42 PM UTC

dcc wrote: post #7

One important distinction is that the strength of LLMs isn't just in storing or retrieving knowledge like Wikipedia, it’s in comprehension. LLMs will return faulty or imprecise information at times, but what they can do is understand vague or poorly formed questions and help guide a user toward an answer. They can explain complex ideas in simpler terms, adapt responses based on the user's level of understanding, and…

> LLMs will return faulty or imprecise information at times

To be fair, so do humans and wikipedia.

Re: Local LLMs versus offline Wikipedia

#40

Post by pinkmuffinere » Sat, Jul 19, 2025, 10:43 PM UTC

nine_k wrote: post #13

pinkmuffinere wrote: post #12

Earlier quoted context omitted.

I’m a massive Wikipedia fan, have a lot of it downloaded locally on my phone, binge read it before bed, etc. Even so, I rarely go through talk pages or version history unless I’m contributing something. What would you see in an article that motivates you to check out the meta layers?

Try any article on a controversial issue.

I guess if I know it’s controversial then I don’t need the talk page, and if I don’t then I wouldn’t think to check