Thursday 29 June 2023

AI Prompt Engineering Trial 1

Community Engagement 1,... 2021 & 22


Update 2: See the next step here in experimenting with AI for good via this CIC
Update 1: See companion Medium article Stop AI scraping your internet data.

The previous post (blog) introduced how our CIC will attempt to find government source data of interest to East Anglia Parishes, in order to assist in creating web pages for all 254 of them. AI is used here to assist the task of seeking information then creating website templates over large numbers of sources to a large number of pages. This is in order to bridge the digital divide of rural citizens and their administrations, which are not plugged into centralised corporate or government ecosystems. We acknowledge the assistance of local Wikimedians (here), who are transforming voluminous IPCC (Wikipedia) reports into text the general public can grasp, retain and take action on.

Among the many AI tools available, Bing AI was chosen for its sheer ease of use, free cost and access to the latest tools (Chat GPT 4). Let's skip the Chat mode, which is like any search engine on steroids, providing a conversational interface, where you can iteratively improve your search via "chatting": for example, the initial search is followed on by a question Bing AI suggested from the highlight section.


click to enlarge

Note: I use the first thing everyone asked when trying new search engines, from Altavista in the nineties thru Google in the noughties, to own location search in the teens... Is it narcissism, or angst about what's publicly available about us?

 Let's go straight to midway my online class: show how a blog post on mapping issues, is created by generating prompts using Bing AI following the STAR (style-task-audience-role) mnemonic for the basic  steps. Here we cut over from Chat to Compose in Bing AI:

click to enlarge

The text is admittedly impressive:
As a mapping expert and blog writer, I often get asked about the challenges and difficulties of creating accurate and reliable maps. In this blog post, I will share with you some of the top issues that map makers face and how they can be overcome or minimized.

One of the most fundamental and complex issues in mapping is the projection system. A projection system is a method of transforming the three-dimensional surface of the earth into a two-dimensional representation on a map. However, there is no perfect projection system that can preserve all the properties of the earth's surface, such as shape, area, distance, direction, and angle. Every projection system involves some trade-offs and distortions, depending on the purpose and scope of the map.

For example, the Mercator projection is widely used for navigation and web mapping because it preserves angles and directions, but it also greatly exaggerates the size of areas near the poles. On the other hand, the Gall-Peters projection tries to show equal areas for all regions, but it distorts their shapes and angles. Therefore, map makers have to choose the most suitable projection system for their specific needs and goals, and be aware of its limitations and biases.

Another important issue in mapping is the spherical datum. A spherical datum is a mathematical model of the shape and size of the earth that serves as a reference for locating points on its surface. However, the earth is not a perfect sphere, but rather an irregular ellipsoid that bulges at the equator and flattens at the poles. Moreover, the earth's shape is constantly changing due to tectonic movements, gravitational variations, sea level changes, and other factors.

Therefore, there are many different spherical datums that have been developed over time and across regions, such as WGS84, NAD83, ED50, GRS80, etc. Each datum has its own origin, orientation, scale, and parameters that define its relationship to the earth's surface. However, not all datums are compatible or consistent with each other, which can cause errors and discrepancies when converting or overlaying data from different sources or formats.

For example, if you use a GPS device that uses WGS84 datum to locate a point on a map that uses NAD83 datum, you may find a difference of up to 100 meters between the two coordinates. Similarly, if you overlay a satellite image that uses WGS84 datum on a topographic map that uses ED50 datum, you may notice some misalignment or distortion of features. Therefore, map makers have to be careful and precise when choosing and applying spherical datums for their data and maps, and be able to convert or transform them when necessary.

 Note that it ends with a further prompt to shorten, as I asked for the long version


click to enlarge


The resulting text is:
As a mapping expert and blog writer, I want to share some of the top issues in creating maps. These are the projection system and the spherical datum.

The projection system is how we transform the 3D earth into a 2D map. But no projection system can keep all the properties of the earth, such as shape, area, distance, direction, and angle. Every projection system has some trade-offs and distortions. For example, the Mercator projection is good for navigation and web mapping, but it makes the areas near the poles look bigger than they are.

The spherical datum is a mathematical model of the earth's shape and size. It helps us locate points on the earth's surface. But the earth is not a perfect sphere, and it changes over time. So there are many different spherical datums that have been used in different times and places. Each datum has its own origin, orientation, scale, and parameters. But not all datums are compatible or consistent with each other. This can cause errors and discrepancies when we use data or maps from different sources or formats.

 And you're prompted to add more details:

As a mapping expert and blog writer, I want to share some of the top issues in creating maps. These are the projection system and the spherical datum. These two issues affect the accuracy and reliability of maps, and they require careful and precise choices and calculations by map makers.

The projection system is how we transform the 3D earth into a 2D map. But no projection system can keep all the properties of the earth, such as shape, area, distance, direction, and angle. Every projection system has some trade-offs and distortions, depending on the purpose and scope of the map. For example, the Mercator projection is good for navigation and web mapping, because it preserves angles and directions, but it makes the areas near the poles look bigger than they are. On the other hand, the Gall-Peters projection tries to show equal areas for all regions, but it distorts their shapes and angles. Therefore, map makers have to choose the most suitable projection system for their specific needs and goals, and be aware of its limitations and biases.

The spherical datum is a mathematical model of the earth's shape and size. It helps us locate points on the earth's surface by using coordinates such as latitude and longitude. But the earth is not a perfect sphere, and it changes over time due to various factors such as tectonic movements, gravitational variations, sea level changes, etc. So there are many different spherical datums that have been used in different times and places. Each datum has its own origin, orientation, scale, and parameters that define its relationship to the earth's surface. But not all datums are compatible or consistent with each other. This can cause errors and discrepancies when we use data or maps from different sources or formats. For example, if you use a GPS device that uses WGS84 datum to locate a point on a map that uses NAD83 datum, you may find a difference of up to 100 meters between the two coordinates. Similarly, if you overlay a satellite image that uses WGS84 datum on a topographic map that uses ED50 datum, you may notice some misalignment or distortion of features. Therefore, map makers have to be careful and precise when choosing and applying spherical datums for their data and maps, and be able to convert or transform them when necessary.

 Or subheadings:

As a mapping expert and blog writer, I want to share some of the top issues in creating maps. These are the projection system and the spherical datum. These two issues affect the accuracy and reliability of maps, and they require careful and precise choices and calculations by map makers.

## Projection System

The projection system is how we transform the 3D earth into a 2D map. But no projection system can keep all the properties of the earth, such as shape, area, distance, direction, and angle. Every projection system has some trade-offs and distortions, depending on the purpose and scope of the map. For example, the Mercator projection is good for navigation and web mapping, because it preserves angles and directions, but it makes the areas near the poles look bigger than they are. On the other hand, the Gall-Peters projection tries to show equal areas for all regions, but it distorts their shapes and angles. Therefore, map makers have to choose the most suitable projection system for their specific needs and goals, and be aware of its limitations and biases.

## Spherical Datum

The spherical datum is a mathematical model of the earth's shape and size. It helps us locate points on the earth's surface by using coordinates such as latitude and longitude. But the earth is not a perfect sphere, and it changes over time due to various factors such as tectonic movements, gravitational variations, sea level changes, etc. So there are many different spherical datums that have been used in different times and places. Each datum has its own origin, orientation, scale, and parameters that define its relationship to the earth's surface. But not all datums are compatible or consistent with each other. This can cause errors and discrepancies when we use data or maps from different sources or formats. For example, if you use a GPS device that uses WGS84 datum to locate a point on a map that uses NAD83 datum, you may find a difference of up to 100 meters between the two coordinates. Similarly, if you overlay a satellite image that uses WGS84 datum on a topographic map that uses ED50 datum, you may notice some misalignment or distortion of features. Therefore, map makers have to be careful and precise when choosing and applying spherical datums for their data and maps, and be able to convert or transform them when necessary.

 A hook: 

 Have you ever wondered how maps are made and why they look the way they do? If you are interested in mapping, you may have noticed that there are many different types of maps, such as political, physical, thematic, topographic, etc. But how do map makers decide what kind of map to use and how to represent the earth's surface on a flat sheet of paper? In this blog post, I will share with you some of the top issues that map makers face and how they can be overcome or minimized. These are the projection system and the spherical datum. These two issues affect the accuracy and reliability of maps, and they require careful and precise choices and calculations by map makers.

## Projection System

The projection system is how we transform the 3D earth into a 2D map. [ ... ]

 A call to action:

[ ... ] Similarly, if you overlay a satellite image that uses WGS84 datum on a  topographic map that uses ED50 datum, you may notice some misalignment or distortion of features. Therefore, map makers have to be careful and precise when choosing and applying spherical 

I hope this blog post has given you some insight into the challenges and complexities of mapping. If you want to learn more about mapping techniques and tools, or if you need help with your mapping projects, please feel free to contact me at [email address]. I would love to hear from you and assist you with your mapping needs.

A conclusion:

[ ... ] In conclusion, mapping is a fascinating and challenging field that involves many technical and artistic decisions. The projection system and the spherical datum are two of the most fundamental and complex issues that map makers have to deal with. By understanding these issues and their implications, we can appreciate the diversity and beauty of maps, as well as their limitations and biases.

I hope this blog post has given you some insight into the challenges and complexities of mapping. If you want to learn more about mapping techniques and tools, or if you need help with your mapping projects, please feel free to contact me at [email address]. I would love to hear from you and assist you with your mapping needs.  

 

click to enlarge

Note: this multi-step process ends up taxing the system, as output slows down markedly toward the end, although it speeds up again presumably reading caches again?

And it keeps offering more avenues for refinement... The last step "Add to site", however,  doesn't appear to work. Let me ask and keep you posted. 

Stay tuned... We will also explore Google Bard & integrate with local Wikimedians. 

Rather than add fuel to the AI fire*, let's find a use case if it'll help digital nomads curtail the digital divide, stated 2½ years ago in the context of the pandemic:

click ot enlarge or go here


* Positive use of AI: Sky reports here upcoming Beatles issue adding deceased voices 50 yrs after band dissolved. Note that 'Macca' is no stranger to innovation, 2014 3D VR version  of 1978 hit Mull of Kintyre (mouse to pan, and begin vid for documentary):


No comments:

Post a Comment

Please send me a copy of your prospectus to