technology analyzing technology

by

I have written almost 100 posts referencing Marshall McLuhan’s Laws of Media using the media tetrad. I recently came across a tweet where the author, Ethan Mollick asked ChatGPT, “Create a Marshall McLuhan tetrad for larger language models. Be creative and insightful. Think like a theorist.” The image below shows the ChatGPT response.

Chat GPT response to the question, “Create a Marshall McLuhan tetrad for larger language models. Be creative and insightful. Think like a theorist.” Marshall McLuhan's tetrad is a way of examining the effects of any technology or medium, and it is organized into four parts: Enhancement, Obsolescence, Retrieval, and Reversal. Here's a tetrad for large language models: Enhancement (What does the technology amplify or intensify?) Large language models enhance the accessibility and scalability of information processing and knowledge synthesis. They amplify the ability for individuals and organizations to interact with vast amounts of information, providing synthesized knowledge, insights, and responses at a speed and scale previously impossible for humans alone. Obsolescence (What does the technology push to the background or replace?) Large language models could potentially make traditional search engines obsolete or at least shift their role. Instead of manually sorting through pages of search results, users can interact conversationally with a model to get synthesized, contextually-appropriate information. Additionally, they may push more manual, time-consuming information synthesis tasks, like some aspects of research or data analysis, into the background. Retrieval (What does the technology bring back that was previously lost?) Large language models retrieve the art of dialogue and the Socratic method of learning, albeit in a different form. They bring back the conversational aspect of information gathering and learning that was largely lost in the era of one-way, impersonal search engines and data retrieval systems. Furthermore, they may revive a more personalized, tailored interaction with technology, reminiscent of the pre-industrial era where products and services were individually crafted. Reversal (What will the technology become if it's overused or pushed to extreme?) If large language models are overused or pushed to the extreme, they could lead to over-reliance on Al for decision-making, potentially diminishing human critical thinking skills. They might also reverse into a source of misinformation or manipulation if their outputs are not properly managed or if they are used unethically. Furthermore, they could become an echo chamber, reinforcing existing beliefs and biases rather than encouraging exploration of diverse perspectives and critical thinking.

The ChatGPT response is similar to my tetrads created for these posts:

GPT-3 through a glass darkly

auto-tuning work

capitalism > automation > gpt

But of course the ChatGPT response would reflect my own. ChatGPT is merely a stochastic parrot of what humans have shared on the web. We are getting scraped by these tools, such as Google’s C4 dataset which in my case was confirmed by the Washington Post.

This use of LLMs has limited value in my opinion. I think a more useful application of LLMs would be in helping individuals interpret complicated pieces of information such as — end-user license agreements, contracts, patient records and diagnoses, user manuals.

McLuhan tetrad according to ChatGPT reformatted

Related Posts

1 thought on “technology analyzing technology”

  1. Pingback: LLM Tetrads (in progress)

Leave a comment

 

This site uses Akismet to reduce spam. Learn how your comment data is processed.