Browse > Home / AI, Business process, Database, News / Good Enough Junk Food: Knowledge without the Work

Good Enough Junk Food: Knowledge without the Work

December 16, 2024

Hopping Dino_thumb_thumbThis write up emerged from the dinobaby’s own mind. Yes, the dinobaby used AI because this write up is about the knowledge value lost with smart software. Intellectual junk food is not the same as my mother’s overcooked chicken which she killed on her aunt’s farm. Cluck, cluck, squawk.

I plugged the Guardian’s opinion essay into You.com’s Chat GPT-4o model. You can read the original essay titled “Is Doom Scrolling Really Rotting Our Brains? The Evidence Is Getting Harder to Ignore.” The original essay is clear, reasonably well researched, and structured to speak to [a] a person who has access to the Guardian online or in (gasp!) a print form, [b] who reads the Guardian’s opinion essays, and [c] who has the ability to recognize that “brain rot” has probably affected that individual, co-workers, government leaders, children, and people who repair refrigerators.

image

This illustration is good enough and it was produced by the AI system Magic Studio.

Here’s the summary Chat GPT-4o spit out:

The essay critiques the decline of human intellect in the digital age, using the viral “Skibidi Toilet” video as a cultural metaphor for deteriorating focus and intellectual engagement. The Oxford English Dictionary’s 2024 word of the year, “brain rot”, reflects this phenomenon, defined as the mental degradation caused by excessive consumption of trivial online content. The essay draws on academic research to demonstrate how compulsive internet use is literally shrinking grey matter, weakening memory, shortening attention spans, and distorting cognitive functions. Studies from Harvard, Oxford, and King’s College reveal the harmful effects of media multitasking and heavy internet usage, with findings such as reduced grey matter in the brain and the risk of “digital dementia” in young people during critical developmental years.The prevalence of infinite scroll and dopamine-driven design in apps is highlighted as a deliberate tactic by tech companies to exploit human psychology for profit, creating powerful addiction loops. Former Google design ethicist Tristan Harris warns that this “race to the bottom of the brain stem” manipulates fear, outrage, and reward systems, potentially driving society to catastrophe if left unchecked.Despite the grim outlook, the essay finds hope in the growing self-awareness among younger generations, who coined the term “brain rot” and recognize its effects. Movements advocating for reduced technology use, such as switching to dumbphones or promoting smartphone-free childhoods, are gaining traction. These trends suggest the possibility of reclaiming mental clarity and focus, countering the current trajectory of cognitive decline.Ultimately, the essay positions “Skibidi Toilet” as both a symptom of modern intellectual decay and a call to action. Humanity stands at a critical juncture: to either rise above the current trends of distraction and degradation or succumb further to the “U-bend” of intellectual regression.

For what it is worth, this is a typical bite-sized knowledge cookie. No one will know if the summary is good or bad unless that person takes the time to get the original full text and compare it with this AI generated output. The informational fast food provides a sugar jolt from saving time or the summary consumer’s belief that the important information is on the money. A knowledge cookie if you will, or maybe intellectual junk food?

Is this summary good enough? From my point of view, it is just okay; that is, good enough. What else is required? Flash back to 1982, the ABI/INFORM database was a commercial success. A couple of competitors were trying to capture our customers which was tricky. Intermediaries like Dialog Information Services, ESA, LexisNexis (remember Buster and his silver jumpsuit?), among others “owned” the direct relationship with the companies that paid the intermediaries to use the commercial databases on their systems. Then the intermediaries shared some information with us, the database producers.

How did a special librarian or a researcher “find” or “know about” our database? The savvy database producers provided information to the individuals interested in a business and management related commercial database. We participated in niche trade shows. We held training programs and publicized them with our partners Dow Jones News Retrieval, Investext, Predicasts, and Disclosure, among a few others. Our senior professionals gave lectures about controlled term indexing, the value of classification codes, and specific techniques to retrieve a handful of relevant citations and abstracts from our online archive. We issued news releases about new sources of information we added, in most cases with permission of the publisher.

We did not use machine indexing. We did have a wizard who created a couple of automatic indexing systems. However, when the results of what the software in 1922 could do, we fell back on human indexers, many of whom had professional training in the subject matter they were indexing. A good example was our coverage of real estate management activities. The person who handled this content was a lawyer who preferred reading and working in our offices. At this time, the database was owned by the Courier-Journal & Louisville Times Co. The owner of the privately held firm was an early adopted of online and electronic technology. He took considerable pride in our line up of online databases. When he hired me, I recall his telling me, “Make the databases as good as you can.”

How did we create a business and management database that generated millions in revenue and whose index was used by entities like the Royal Bank of Canada to index its internal business information?

Here’s the secret sauce:

  1. We selected sources in most cases business journals, publications, and some other types of business related content; for example, the ANBAR management reports
  2. The selection of which specific article to summarize was the responsibility of a managing editor with deep business knowledge
  3. Once an article was flagged as suitable for ABI/INFORM, it was routed to the specialist who created a summary of the source article. At that time, ABI/INFORM summaries or “abstracts” were limited to 150 words, excluding the metadata.
  4. An indexing specialist would then read the abstract and assign quite specific index terms from our proprietary controlled vocabulary. The indexing included such items as four to six index terms from our controlled vocabulary and a classification code like 7700 to indicate “marketing” with addition two digit indicators to make explicit that the source document was about marketing and direct mail or some similar subcategory of marketing. We also included codes to disambiguate between a railroad terminal and a computer terminal because source documents assumed the reader would “know” the specific field to which the term’s meaning belonged. We added geographic codes, so the person looking for information could locate employee stock ownership in a specific geographic region like Northern California, and a number of other codes specifically designed to allow precise, comprehensive retrieval of abstracts about business and management. Some of the systems permitted free text searching of the abstract, and we considered that a supplement to our quite detailed indexing.
  5. Each abstract and index terms was checked by a control control process using people who had demonstrated their interest in our product and their ability to double check the indexing.
  6. We had proprietary “content management systems” and these generated the specific file formats required by our intermediaries.
  7. Each week we updated our database and we were exploring daily updates for our companion product called Business Dateline when the Courier Journal was broken up and the database operation sold to a movie camera company, Bell+Howell.

Chat GPT-4o created the 300 word summary without the human knowledge, expertise, and effort. Consequently, the loss of these knowledge based workflow has been replaced by a smart software which can produce a summary in less than 30 seconds.

And that summary is, from my point of view, good enough. There are some trade offs:

  1. Chat GPT-4o is reactive. Feed it a url or a text, and it will summarize it. Gone is the knowledge-based approach to select a specific, high-value source document for inclusion in the database. Our focus was informed selection. People paid to access the database because of the informed choice about what to put in the database.
  2. The summary does not include the ABI/INFORM key points and actionable element of the source document. The summary is what a high school or junior college graduate would create if a writing teacher assigned a “how to write a précis” as part of the course requirements. In general, high school and junior college graduates are not into nuance and cannot determine the pivotal information payload in a source document.
  3. The precise indexing and tagging is absent. One could create a 1,000 such summaries, toss them in MISTRAL, and do a search. The result is great if one is uninformed about the importance of editorial polices, knowledge-based workflows, and precise, thorough indexing.

The reason I am sharing some of this “ancient” online history is:

  1. The loss of quality in online information is far more serious than most people understand. Getting a summary today is no big deal. What’s lost is simply not on these individuals’ radar.
  2. The lack of an editorial policy, precise date and time information, and the fine-grained indexing means that one has to wade through a mass of undifferentiated information. ABI/INFORM in the 1080s delivered a handful of citations directly on point with the user’s query. Today no one knows or cares about precision and recall.
  3. It is now more difficult than at any other time in my professional work career to locate needed information. Public libraries do not have the money to obtain reference materials, books, journals, and other content. If the content is online, it is a dumbed down and often cut rate version of the old-fashioned commercial databases created by informed professionals.
  4. People look up information online and remain dumb; that is, the majority of the people with whom I come in contact routinely ask me and my team, “Where do you get your information?” We even have a slide in our CyberSocial lecture about “how” and “where.” The analysts and researchers in the audience usually don’t know so an entire subculture of open source information professionals has come into existence. These people are largely on their own and have to do work which once was a matter of querying a database like ABI/INFORM, Predicasts, Disclosure, Agricola, etc.

Sure the essay is good. The summary is good enough. Where does that leave a person trying to understand the factual and logical errors in a new book examining social media. In my opinion, people are in the dark and have a difficult time finding information. Making decisions in the dark or without on point accurate information is recipe for a really bad batch of cookies.

Stephen E Arnold, December 15, 2024

Written by Stephen E. Arnold · Filed Under AI, Business process, Database, News 

Comments

Got something to say?





  • Archives

  • Recent Posts

  • Meta