[heart] Janis McKenzie reacted to your message:
________________________________
From: Code for Libraries <CODE4LIB_at_LISTS.CLIR.ORG> on behalf of Stephen Marks <0000028e9ae84289-dmarc-request_at_LISTS.CLIR.ORG>
Sent: Friday, 29 May 2026 16:44:28
To: CODE4LIB_at_LISTS.CLIR.ORG <CODE4LIB_at_LISTS.CLIR.ORG>
Subject: Re: [CODE4LIB] llm technology is especially useful
Hi Eric--
I'm a long time code4lib member but a rare poster. I've long been an admirer of both you and Roy, so reading two AI apologia pieces in a row got me thinking. I was writing a reply to Roy's piece, but in reading yours, I think things crystallized for me significantly.
*
Granted there are environmental costs. Hmmm... Are there moral costs? That is to be discussed too. Are there professional issues? To be sure!
I think for many folks, these concerns bear a good deal more scrutiny than provided here, and can't just be glossed over just because the model was able to offer a passable summary of a text archive.[1]
I think these three buckets (environmental, copyright, and labour) each represent a significant tangle of very real concerns that need to be worked through before many of our colleagues would offer a more ringing endorsement of said technologies. I know people who are passionate about the first two, but it isn't me, but I have spent a lot of time thinking about the third one.
Early on, I read a think piece somewhere (idk realistically probably reddit) that suggested that, given the significant resources being put into the AI space, we might take a moment to think about what problem the people making all that money are trying to solve. And the only answer I came up with out of that was labour. They're trying to solve the problem of having to pay people.
That's not to say that there aren't short term gains to be made by us individually by leveraging these technologies in our current employment. But I do think ultimately we all anticipate a day when, having been glutted on thousands upon thousands of records of reference interviews and sensemaking pieces, some LLM or another is sold right back to libraries by one of our multinational vendors as a solution to having to train, retain, and develop staff to do this stuff.
And maybe it all evens out over time, but looking at the big picture is a luxury of people like you and me who are easily in the back half of our careers. Most folks on this list (and libraries in general I'd guess) are in a very much precarious situation, and such disruption stands to have a real and present effect on their day to day lives.
Anyway, that's all. Those three buckets are why I think libraryland isn't crazy about AI stuff in general.
Again, much love and the greatest amount of respect.
Steve
[1]: Side note: I'd argue, contrary to your assertion, you did not "quickly and easily read, make sense of, and learn from a large corpora"! You got a relatively facile summary that could have been written by anyone, and you were able to be relatively sure of its truth because you have many years of familiarity with the field and your brain filled in a lot of the gaps in the explainer.
________________________________
From: Code for Libraries <CODE4LIB_at_LISTS.CLIR.ORG> on behalf of Eric Lease Morgan <00000107b9c961ae-dmarc-request_at_LISTS.CLIR.ORG>
Sent: Friday, May 29, 2026 10:17 AM
To: CODE4LIB_at_LISTS.CLIR.ORG <CODE4LIB_at_LISTS.CLIR.ORG>
Subject: [CODE4LIB] llm technology is especially useful
I assert the use of LLM technology is especially useful -- an accurate time-saver -- when it is applied to one's own content.
For example, I scraped one year's worth of Code4Lib mailing list postings, 2008 to be exact. I then used natural language processing to count and tabulate different types of words from the postings: unigrams, bigrams, keywords, parts-of-speech words, and named-entities. I then fed these counts and tabulations to an LLM (gpt-oss:120b-cloud accessed through Ollama) and asked the model to characterize the postings. Here is the result:
The code4lib‑email carrel reads like a dynamic,
conversational forum dedicated to library‑technology. Its
lexical profile is dominated by first‑person pronouns and
informal markers, indicating a community that constantly
exchanges ideas and asks for help. Core nouns such as
library, web, metadata, software, and API appear with high
frequency, while adjectives like open, digital, free, and
available stress a strong commitment to open‑source and
accessible solutions. Frequently occurring verbs (use,
share, provide, think, ask) and bigrams such as "open
source," "I think," and "you want" reveal an action‑oriented
dialogue centered on problem‑solving, code sharing, and
collaborative refinement of library services.
I wanted to know about open source software, so I: 1) identified a set of sentences containing the phrase "open source software", used the LLM to summarize the result, and then asked it to address the question "What are the advantages and disadvantages of open source software?". Here are the results:
This text is a collection of discussions and announcements
centered around open source software in the context of
libraries, drawn from what appears to be a mailing list or
forum (possibly CODE4LIB). Key themes include the promotion
and benefits of open source software—emphasizing user
freedom, community collaboration, and independence from
proprietary vendors—as well as practical challenges like
software compilation, distribution, and implementation in
library settings.
Based on the provided text, the primary advantage of open
source software is the freedom it grants users through the
absence of proprietary control. This freedom allows the code
to be modified by anyone to suit their needs, liberating
users from being at the mercy of closed-source vendors with
their forced upgrades and compatibility issues. It is
described as being about community, where usability takes
priority over profitability. A noted disadvantage, however,
is that the open-source model shifts most of the costs from
acquisition to operations and maintenance. Furthermore,
introducing open source development in organizations
accustomed to vendor-based relationships requires
significant change management.
I did the same thing but this time regarding MARC: What are the advantages and disadvantages of MARC? Here are the results:
This email thread is a sprawling discussion among librarians
and tech folks on the Code4Lib mailing list, focusing
heavily on MARC records—the standard format for library
catalog data. The conversation covers a range of topics,
including technical challenges with processing MARC data
(like character encoding issues and parsing), tools for
working with MARC (such as MarcEdit, MARC4J, and others),
and debates around the limitations and flexibility of the
MARC format itself.
Based on the provided source material, the advantages and
disadvantages of MARC are not explicitly detailed in a
structured or comprehensive manner. However, some insights
can be inferred from the fragmented discussions. MARC is
noted for its flexibility as a data structure, having been
designed to exploit the technological environment of its
time effectively, which suggests it was once well-suited to
library needs. On the other hand, it is described as an
"annoying data format," with limitations such as issues with
character encodings during conversion and a rigid record
length constraint in its leader field, reflecting its age
and the challenges of adapting it to modern systems.
Additionally, the complexity of parsing MARC data is
mentioned, alongside the need for specialized tools or
conversion to more manageable formats like MODS or MARCXML
to improve usability.
The results are not only plausible but I assert they are true and accurate. Thus, using a combination of natural language processing and LLM technology I was able to quickly and easily read, make sense of, and learn from a large corpora. [1] Even more, I can apply this process to any corpora, large or small: a book, a set of books, a few journal articles, hundreds of journal articles, etc.
What does this cost? Financially, very little. I pay $20/month to use Ollama's cloud services. Computer-wise all of this can be done on a laptop computer, but the process is quicker and easier when I use my 64-core Linux computer. Granted there are environmental costs. Hmmm... Are there moral costs? That is to be discussed too. Are there professional issues? To be sure!
All that said, we all continue to suffer from information overload. Libraries are a part of that problem. Just look at the size of your library's collection. Not small? The application of natural language processing and LLMs can make our collections more useful, and isn't that the point? To make our collections useful?
If all of this is true, then why, when it comes to LLM technology, do I feel there is so much trepidation in Library Land? What am I missing? I'd really like to know.
Note
[1] The corpus includes about 2,200 postings for a total of .79 million words. By comparison, the Bible is about .8 million words long, Melville's Moby Dick is about .25 million words long, and based on my experience, the typical scholarly journal article is about .007 million words long.
--
Eric Lease Morgan <emorgan_at_nd.edu>
Librarian Emeritus, University of Notre Dame
Received on Fri May 29 2026 - 14:05:32 EDT