Let GPT4 create the metaphor.

In the recent experiment “[Divergence and abstraction in GPT4 in metaphor space and then concretization. This was because I happened to be thinking in advance about the relationship between “new ways of working” and “nomads. This time, let GPT4 create the metaphor itself.

• The Intellectual Production of Engineers p.196 and have GPT4 do the method.
• 
  • Corresponding, associating, and drawing back

You are good at thinking by analogy. I give you a concept X. You compare X to another concrete thing Y. Then you list the features of Y. Finally, you map those features to the features of X. Can you do it?

X = apple

Of course you can. Now, let us consider the analogy of concept X “apple” with concrete thing Y “earth”.

The following is a list of characteristics about Y “Earth”.

1. round shape
2. various topographic features exist on the surface
3. rotating on its own axis and revolving in orbit
4. life exists
5. there is an atmosphere and a changing climate

Next, we map these characteristics to the characteristics of X “apples”.

1. round shape - Apples, like the earth, have a round shape.
2. various topographic features exist on the surface - the unevenness and color variation of the apple’s peel and the individuality of its surface can be mapped to the topography of the earth.
3. spinning and orbiting - Apples do not spin or orbit themselves, but the fruit may rotate during the growth process to ensure equal exposure to sunlight.
4. life exists - Apples are similar to the earth in that they have seeds that give birth to new apple trees, thus continuing the cycle of life.
5. has an atmosphere and a variable climate - Apples themselves do not have an atmosphere or climate, but they do need the right climate and environment to grow, and in this respect they are related to the earth.

X = intellectual production

Let’s compare concept X “intellectual production” to concrete thing Y “cooking”.

Y List the characteristics of the “cuisine”.

1. combining materials
2. different recipes and methods yield different results
3. experience and knowledge affect quality
4. adjustable to individual preferences and needs
5. it is a creative process

Next, we map these characteristics to those of X “intellectual production”.

1. combine materials - In intellectual production, different information and ideas are combined to produce new knowledge and output.
2. different recipes and methods yield different results - even in intellectual production, different research methods and approaches yield different results.
3. experience and knowledge affect quality - The quality of intellectual production is largely determined by an individual’s experience and expertise.
4. tailored to individual preferences and needs - Intellectual production can also be tailored to the needs and interests of the target audience.
5. it is a creative process - intellectual production is a creative process that generates new ideas and solutions.

I want to know how to improve my intellectual production using AI. First list the ways to improve cooking, then project it to intellectual production using AI.

First, we list ways to improve the food.

1. recipe optimization
2. material selection and quality control
3. improvement of cooking methods and procedures
4. introduction of new technologies and tools
5. accept feedback and improve

We then project these improvement methods into AI-based intellectual production.

1. recipe optimization - AI can be used to find the best solution from existing knowledge and data. This allows for an efficient and effective intellectual production process.
2. material selection and quality control - AI can select the best information sources and data sets to support quality intellectual production.
3. improved cooking methods and procedures - AI can optimize research methods and approaches and streamline the process of intellectual production.
4. introduction of new technologies and tools - AI and machine learning can be used to introduce new technologies and methods into intellectual production to produce more advanced results.
5. accept and improve feedback - AI can analyze historical data and results to identify problems and areas for improvement. This allows for improvements in the intellectual production process.

impressions

• The methodology of intellectual production is like a recipe for cooking. Until now, humans have read the recipe and cooked the food.
• AI helps gather “good material”
• AI can serve as a “new tool” like a microwave oven or food processor
• Creating a delicious dish is not the same as creating a recipe for a dish.
  • If you can’t cook a good dish, you can’t cook a good recipe.
  • Sharing good recipes helps many people cook better
  • This is “raising (the standard)” .
    • Following a recipe doesn’t mean you can do the same thing as a chef in a famous hotel.
    • Be able to quickly make a paste out of potatoes.

---

This page is auto-translated from /nishio/GPT4にメタファーを作らせる using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.