Volume 2 – Handbook I: Authors Profiles – Looking for Reading & Writing “Process” Efficiencies with GPT

For new readers, please read the “Pinned Post” at the top of this Substack’s Home Page, and titled Why Use Public Peer-Review to Write a Book? - “See for Yourself”.

For returning readers & subscribers, this post presents a GPT-assisted review of the last 8 author profiles (Out of a current total of 21 such profiles at this time). These 8 profiles include: Hannah Arendt, Edward Bernays, Gerd Gigerenzer, Richard Hamming, Elton McGoun, H.L. Mencken, C.K. Ogden, & W.S. George Trow.

Writing these Author Profiles requires reading paper copies of the studies & books mentioned in the sources. This process is expensive, and takes linear time. This dual expense of resources triggered curiosity about what non-linear efficiencies could be gained from using GPT in the writing of such posts, perhaps at the added cost of vetting GPT’s uncertain accuracy, and precision.

What might GPT find as the most probable completion steps when given a running start with an author’s name, and a writing process that uses a structure derived from the “Template for Reading Research Papers”?

Further, reading recent posts from other Substack authors in the context of the earlier post, and author profile about W. S. George Trow, I wondered where GPT’s answers might stand on a spectrum that reflects a writer’s positioning in the “Economy of Attention”. This spectrum ranges from outrage-filled, headline-like answers that trigger short-term dopamine peaks - shown on the left-side of the spectrum - to thoughtful discussions that deliver sustained serotonin increases - shown on the right-side of the spectrum.

Using a series of prompts to familiarize GPT with our full list of foundational authors, a final prompt asked for summaries based on the structure of these Author Profiles. GPT returned the following summarizes that you can compare to the previously published Author Profiles.

Note that GPT omitted Elton “Skip” McGoun, and H.L. Mencken. While it did provide a reasonable summary for Mencken in a re-try, GPT delivered a complete hallucination for McGoun including the fabrication of incorrect birth/death dates, and nature of the body of work.

Hannah Arendt (1906–1975):

Perspective: Political philosopher who explored concepts of authority, power, and totalitarianism.

Historical Context: Witnessed the rise of totalitarian regimes during the mid-20th century.

Purpose: To understand the impact of authoritarianism and the nature of political power on shared humanity.

Methodological Choices: Philosophical analysis and historical reflection.

Edward Bernays (1891–1995):

Perspective: Pioneer in public relations and propaganda.

Historical Context: Lived through the rise of mass media and advertising.

Purpose: To influence public opinion and behavior through persuasive communication.

Methodological Choices: Applied psychology, mass communication, and public relations techniques.

Gerd Gigerenzer (1947–present):

Perspective: Psychologist known for work on heuristics and decision-making.

Historical Context: Influential in the field of psychology during the late 20th and early 21st centuries.

Purpose: To challenge traditional views of rationality and explore how heuristics affect decisions.

Methodological Choices: Empirical research and cognitive psychology.

Richard Hamming (1915–1998):

Perspective: Mathematician and computer scientist known for work on error-correcting codes and Hamming distance.

Historical Context: Active during the mid-20th century, a pivotal period in computing and information theory.

Purpose: To improve the reliability of information systems and data transmission.

Methodological Choices: Mathematical analysis and coding theory.

C.K. Ogden (1889–1957):

Perspective: Linguist and philosopher who developed Basic English and explored the relationship between language and thought.

Historical Context: Active during the early to mid-20th century.

Purpose: To examine the influence of language on human thought and behavior.

Methodological Choices: Linguistic analysis and semantics.

George W.S. Trow (1943–2006):

Perspective: Writer and cultural critic known for commentary on media, culture, and language.

Historical Context: Influential during the latter half of the 20th century.

Purpose: To explore how media and culture shape human behavior and decision-making.

Methodological Choices: Literary and cultural analysis.

At a minimum, GPT returned the correct birth and death years, and the content of these summaries looks plausible. However, these single sentence summaries feel very “Newsy”, reminiscent of famous newspaper headlines such as “Austere Religious Scholar”, thus missing the meaningful connections.

Further, and unsurprisingly, repeated efforts to find otherwise hidden connections between these authors did not return anything novel, or insightful. Completions based on the most probable next term, sentence, paragraph, or idea given one’s training do not amount to a “Process” of connecting the dots creatively.

However, GPT did group the full list of authors by relevant body of knowledge in a useful, and consistent manner. Similarly, it did group the full list into timelines based on dates of birth/death. Validating the accuracy of GPT’s answers led to the creation of an Excel worksheet to match the references, and connections from author profile to author profile. This worksheet highlighted missing connections in some of the existing Author profiles, adding a new step in this “Process” of public, peer-review.

Finally, GPT provided additional names of foundational authors that include: Albert Bandura, Jean Piaget, Peter Drucker, & W. Edward Deming. It also added Nassim Nicholas Taleb, & Yuval Noah Harari. What do you think of these suggested additions to the list? Who would you remove, or else add to the list?

The bottom-line about using GPT as a “Tool” to emulate the human work that goes into writing these posts in general, and the author profiles in particular:

-         Interesting but validating the answer becomes time-consuming,

-         A good value for “Checklist”-based work, but

-         Not particularly useful for the emergence of creative connections.

Back to buying books, reading, and writing the hard way.

“CTRI by Francois Gadenne” writes a book in three volumes, published at the rate of one two-pages section per day on Substack for public peer-review. The book connects the dots of life-enhancing practices for the next generation, free of controlling algorithms, based on the lifetime experience of a retirement age entrepreneur, & continuously updated with insights from reading Wealth, Health, & Statistics (i.e. AI/ML/LLM) research papers on behalf of large companies as the co-founder of CTRI.