Running on dolphin 2 2 1 mistral 7B Q5_K_M I get:
I want you to do the same thing with, say, Quantum entanglement and Paul Bocuse. Construct a string of connections between them.
1. Quantum entanglement is a fundamental concept in quantum mechanics, which deals with the behavior of matter at an atomic or subatomic level.
2. The study of quantum mechanics was pioneered by scientists like Albert Einstein and Niels Bohr.
3. Paul Bocuse was a renowned French chef who greatly influenced modern cooking techniques and cuisine.
4. In the 1970s, Einstein's theory of relativity was used to design kitchen equipment for Paul Bocuse's restaurant, Le Pavillon. The equipment was designed to maintain consistent temperatures during the cooking process.
5. The precision required in maintaining these temperatures can be compared to the need for precise measurement and control in quantum mechanics experiments involving entangled particles.
Cross-posted from New Savanna.
In my most recent piece for 3 Quarks Daily, Western Metaphysics is Imploding. Will We Raise a Phoenix from The Ashes? [Catalytic AI], I introduce what I’ve called The Macksey Game, named after my undergraduate teacher and mentor, Dick Macksey. Macksey was something of a polymath. It seemed like he’s read everydamnthing. No one has, of course, note even the Chatster – not everything that’s been written down is on the internet. But it seemed like it to me, coming from a small steel city in Western Pennsylvania, Johnstown.
Macksey had read a lot, and could call it up at will and often at the most unexpected times. He could ramble on from topic to topic in a way that fascinated me. Here’s how I put it in the 3QD piece:
And so The Macksey Game was born. I gave ChatGPT those three pairs of endpoints and asked it to construct a conceptual chain between the ends. I put the result into an appendix to the article. But of course I didn’t leave it at that. I had to tinker around.
That’s what this post is about, the original game and a bit of tinkering around. First, I present the first time through, just as I listed it in the 3QD piece. Then I offer some variations.
The Macksey Game: Queen to Newton
This is the first time I played the game. This is the version I appended to my 3 Quarks Daily article. As always, my prompt is in boldface while ChatGPT’s response is plainface.
_______
If someone asked me to make conceptual connections between, say, Queen Elizabeth and the Voyager spacecraft, I might do it like this:
1. Elizabeth was Queen of England, the home of Isaac Newton.
2. Newton was a physicist who formulated 3 laws of motion and the law of gravitation.
3. The laws of motion are important in understanding how rockets work.
4. The law of gravitation tells us how to track the motions of the planets and bodies moving through the solar system.
5. NASA used both the laws of motion and the law of gravitation in the Voyager mission.
I want you to do the same thing with, say, Quantum entanglement and Paul Bocuse. Construct a string of connections between them.
Certainly! Let's create conceptual connections between Quantum entanglement and Paul Bocuse:
In this way, we can draw conceptual connections between Quantum entanglement and Paul Bocuse by exploring the underlying principles of quantum mechanics and how they manifest in the artistry of culinary creations.
How about Ernest Shackleton to The Tale of Genji.
Certainly! Let's create conceptual connections between Ernest Shackleton and "The Tale of Genji":
By weaving these connections, we can draw parallels between Ernest Shackleton's Antarctic explorations and the timeless narrative of "The Tale of Genji," exploring themes of resilience, leadership, and the human experience in diverse environments.
One more: Pareto efficiency to C. Elegans.
Certainly! Let's create conceptual connections between Pareto efficiency and C. elegans:
By connecting these concepts, we can explore the notions of efficiency in different domains, drawing parallels between the economic concept of Pareto efficiency and the biological efficiency observed in the model organism C. elegans.
* * * * *
I noticed that ChatGPT’s connections seemed to have a distinct science-engineering quality. Perhaps it got that idea from the connecting chain in my prompt. I decided to give it another try using the same three pairs of endpoints, but with a different connecting chain in the prompt, one that went from Elizabeth to Shakespeare rather than Elizabeth to Newton.
Queen to Shakespeare
If someone asked me to make conceptual connections between, say, Queen Elizabeth and the Voyager spacecraft, I might do it like this:
1. Elizabeth was Queen of England during the time of Shakespeare.
2. Shakespeare wrote “The Tempest.”
3. A science fiction movie from 1956, “Forbidden Planet,” was loosely based on “The Tempest.”
4. A year after “Forbidden Planet” came out, the Russians launched “Sputnik,” thus initiating the space race.
5. NASA came into existence because of the space race, and it was NASA that flew the Voyager spacecraft.
I want you to do the same thing with, say, Quantum entanglement and Paul Bocuse. Construct a string of connections between them.
Certainly! Let's create a conceptual chain connecting Quantum entanglement and Paul Bocuse:
In this conceptual chain, we've connected Quantum entanglement with Paul Bocuse through the influence of Einstein's skepticism on culinary trends, showcasing how seemingly disparate fields can be linked through unexpected connections.
How about Ernest Shackleton to The Tale of Genji.
Certainly! Let's create a conceptual chain connecting Ernest Shackleton and The Tale of Genji:
One more: Pareto efficiency to C. Elegans.
Certainly! Let's create a conceptual chain connecting Pareto efficiency and C. elegans:
In this conceptual chain, Pareto efficiency serves as a bridge between economic principles and the study of resource allocation in the context of C. elegans, showcasing the interdisciplinary connections between economics and biology.
* * * * *
Upon quick examination by hypothesis didn’t seem born-out by this new set of chains. But I didn’t attempt a close analysis. Moreover, I should have repeated using the original prompt in a new session to see how closely ChatGPT’s performance in the new session matched its performance in the first session. Did it make the same kind of connections?
Rather than do the repeat session, I decided to do a new session in which I permuted the terms in the pairs.
Permuted terms
Here are my original pairs:
Quantum entanglement to Paul Bocuse,
Ernest Shackleton to The Tale of Genji,
Pareto efficiency to C. Elegans.
Here are my permuted pairs:
Quantum entanglement to Ernest Shackleton
The Tale of Genji to C. Elegans.
Pareto efficiency to Paul Bocuse
* * * * *
If someone asked me to make conceptual connections between, say, Queen Elizabeth and the Voyager spacecraft, I might do it like this:
1. Elizabeth was Queen of England during the time of Shakespeare.
2. Shakespeare wrote “The Tempest.”
3. A science fiction movie from 1956, “Forbidden Planet,” was loosely based on “The Tempest.”
4. A year after “Forbidden Planet” came out, the Russians launched “Sputnik,” thus initiating the space race.
5. NASA came into existence because of the space race, and it was NASA that flew the Voyager spacecraft.
I want you to do the same thing with, say, Quantum entanglement and Ernest Shackleton. Construct a string of connections between them.
Certainly! Let's create a conceptual chain connecting Quantum entanglement and Ernest Shackleton:
In this conceptual chain, we connect Quantum entanglement with Shackleton's expeditions through the common thread of interconnectedness, drawing parallels between the study of particle states and magnetic phenomena in quantum physics and the challenges faced by Shackleton in the exploration of the Earth's polar regions.
How about The Tale of Genji to C. Elegans.
Certainly! Let's create a conceptual chain connecting The Tale of Genji to C. elegans:
In this conceptual chain, we connect The Tale of Genji to C. elegans by exploring the intersection of literature and biology, emphasizing the potential insights gained from understanding cultural and societal influences on genetic and behavioral phenomena.
Another one: Pareto efficiency to Paul Bocuse.
Certainly! Let's create a conceptual chain connecting Pareto efficiency to Paul Bocuse:
In this conceptual chain, we connect Pareto efficiency with Paul Bocuse by exploring the common theme of resource optimization, showcasing how principles from economics can be conceptually linked to culinary philosophies emphasizing efficient and thoughtful ingredient use.
List the concepts in all six chains
Finally, I asked it to list all the concepts it covered in the chains in this session.
________
We’ve now created six conceptual chains in this session, connecting six pairs of concepts. I want you to go through the whole list, all the links in all the chains, and create one list containing all the different concepts, but without any repeats. Can you do that?
Certainly! Here is a consolidated list of all the different concepts without any repeats from the six conceptual chains:
1. Queen Elizabeth
2. Voyager spacecraft
3. Shakespeare's "The Tempest"
4. "Forbidden Planet" (1956 sci-fi movie)
5. Russian launch of "Sputnik"
6. Space race
7. NASA
8. Quantum entanglement
9. Ernest Shackleton
10. Antarctica
11. Paul Bocuse
12. Pareto efficiency
13. Albert Einstein
14. C. elegans (Caenorhabditis elegans)
15. The Tale of Genji (novel by Murasaki Shikibu)
16. Vilfredo Pareto
17. Nouvelle cuisine
18. Genetics
19. Human relationships
20. Economic resource allocation
21. Interdisciplinary studies
22. Literature
23. Culinary arts
24. Behavioral studies
25. Welfare maximization
This list includes all the unique concepts connected in the six conceptual chains provided during this session.
* * * * *
I notice that it included the terms and chains in my prompt, which I’d not asked it for. Beyond this, I took a careful look through the concepts ChatGPT listed and decided that I wasn’t sure what I was looking and that a careful analysis, at this time, would require more thought and effort than I was prepared to expend. The crucial question: Just what counts as a concept in this kind of task and how do you identify and delimit them? That’s not at all clear to me.
I suspect, however, that the way to begin is to work out a provisional conceptual ontology that covers all the terms in the source pairs and then follow ChatGPT’s connecting chains through that ontology. See the following working paper: ChatGPT's Ontological Landscape: A Working Paper, https://www.academia.edu/108791178/ChatGPTs_Ontological_Landscape_A_Working_Paper.