Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Local LLMs versus offline Wikipedia

evanhahn.com

Post reply on HN
Print view View original

51–60 of 200 posts

Re: Local LLMs versus offline Wikipedia

#51

Post by redserk »

ranger_danger wrote: post #39
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.

It appears there's an expectation many non-tech people have that humans can be incorrect but refuse to hold LLMs to the same standard, despite warnings.

Re: Local LLMs versus offline Wikipedia

#52

Post by internetter »

redserk wrote: post #51
ranger_danger wrote: post #39

Earlier quoted context omitted.

> LLMs will return faulty or imprecise information at times To be fair, so do humans and wikipedia.

It appears there's an expectation many non-tech people have that humans can be incorrect but refuse to hold LLMs to the same standard, despite warnings.

On average, it is reasonable to expect that wikipedia will be more correct than an LLM

Re: Local LLMs versus offline Wikipedia

#53

Post by QuadmasterXLII »

antonkar wrote: post #5

A bit related: AI companies distilled the whole Web into LLMs to make computers smart, why humans can't do the same to make the best possible new Wikipedia with some copyrighted bits to make kids supersmart? Why kids are worse than AI companies and have to bum around?)

I think thats a library?

Re: Local LLMs versus offline Wikipedia

#54

Post by folkrav »

lblume wrote: post #21
folkrav wrote: post #15

Earlier quoted context omitted.

Eh, even just “countries that are not the US” would be a correct statement. US tech salaries are just in an entire different ballpark to what most companies outside the US can offer. I’m in Canada, I make good money (as far as Canadian salaries go), but nowhere near “buy an expensive laptop whenever” money.

It may also come down to laptops being produced and sold mostly by US companies, which means that the general fact of most items (e.g. produce) being much more expensive in the US compared to, say, Europe doesn't really apply.

Sure, maybe. In the end, what makes an expense big or not is which proportion of their income goes towards it. Most of the rest of the world has (much) lower salaries, and as you pointed out, often higher cost for equipment. Therefore, the purchase is/feels larger.

Re: Local LLMs versus offline Wikipedia

#55

Post by JKCalhoun »

vFunct wrote: post #2

Why not both? LLM+Wikipedia RAG

Yeah, wanting to try to do that.

Someone posted this recently: https://github.com/philippgille/chromem-go/tree/v0.7.0/examp...

But it is a very simplified RAG with only the lead paragraph to 200 Wikipedia entries.

I want to learn how to encode a RAG of one of the Kiwix drops — "Best of Wikipedia" for example. I suppose an LLM can tell me how but am surprised not to have yet stumbled upon one that someone has already done.

Re: Local LLMs versus offline Wikipedia

#57

Post by jjice »

simonw wrote: post #4

This is a sensible comparison. My "help reboot society with the help of my little USB stick" thing was a throwaway remark to the journalist at a random point in the interview, I didn't anticipate them using it in the article! https://www.technologyreview.com/2025/07/17/1120391/how-to-r... A bunch of people have pointed out that downloading Wikipedia itself onto a USB stick is sensible, and I agree with them. Wikipedi…

Oh interesting idea to use SQLite and their FTS. I was very impressed by the quality of their FTS and this sounds like a great use case.

Re: Local LLMs versus offline Wikipedia

#58

Post by loloquwowndueo »

ozim wrote: post #8
loloquwowndueo wrote: post #3

Earlier quoted context omitted.

Because old laptop that can’t run a local LLM in reasonable time.

Most people who can nag about old laptops on HN can just afford newer one but are cheap as Scrooge Mcduck.

I mean, sure, but this was mentioned in the article, I didn’t make it up:

“Offline Wikipedia will work better on my ancient, low-power laptop.”

Re: Local LLMs versus offline Wikipedia

#59

Post by camel-cdr »

simonw wrote: post #4

This is a sensible comparison. My "help reboot society with the help of my little USB stick" thing was a throwaway remark to the journalist at a random point in the interview, I didn't anticipate them using it in the article! https://www.technologyreview.com/2025/07/17/1120391/how-to-r... A bunch of people have pointed out that downloading Wikipedia itself onto a USB stick is sensible, and I agree with them. Wikipedi…

reposting a comment of mine from a few weeks ago:

> All digitized books ever written/encoded compress to a few TB.

I tied to estimate how much data this actually is in raw text form:

    # annas archive stats
    papers = 105714890
    books = 52670695
    
    # word count estimates
    avrg_words_per_paper = 10000
    avrg_words_per_book = 100000
    
    words = (papers*avrg_words_per_paper + books*avrg_words_per_book )
    
    # quick text of 27 million words from a few books
    sample_words = 27809550
    sample_bytes = 158824661
    sample_bytes_comp = 28839837 # using zpaq -m5
    
    bytes_per_word = sample_bytes/sample_words
    byte_comp_ratio = sample_bytes_comp/sample_bytes
    word_comp_ratio = bytes_per_word*byte_comp_ratio
    
    print("total:", words*bytes_per_word*1e-12, "TB") # total: 30.10238345855199 TB
    print("compressed:", words*word_comp_ratio*1e-12, "TB") # compressed: 5.466077036085319 TB
So uncompressed ~30 TB and compressed ~5.5 TB of data.

That fits on three 2TB micro SD cards, which you could buy for a total of 750$ from SanDisk.

Re: Local LLMs versus offline Wikipedia

#60

Post by colechristensen »

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.

it's fun that i carry around a little box with vaguely correct information about mostly everything i could ask for
Post reply on HN