Episode 12: Hollywood AI Blunder, AI Image Generator Roundup, Google Lens Saves You Time Researching, Use AI For Translation

In this week’s episode of “The Family History AI Show,” my co-host Mark Thompson and I take you on an exhilarating journey through the latest AI advancements revolutionizing genealogy. We kick things off with a cautionary tale from Hollywood, highlighting the critical importance of fact-checking AI-generated content. Then, we dive deep into the world of AI image generators, exploring tools like DALL-E, Midjourney, and Adobe Firefly, and discussing their potential to breathe new life into family history narratives. We’re particularly excited to share our insights on the game-changing updates to Google Lens and its integration with Chrome, which we believe will transform how genealogists interact with online content. Our “Tip of the Week” focuses on the versatile applications of AI in translation, going far beyond simple language conversion. We wrap up with our “RapidFire” segment, covering everything from Microsoft’s new Tab Organizer to the future of AI agents in research. Whether you’re a tech enthusiast or just starting to explore AI’s role in genealogy, this episode is packed with practical advice and inspiring ideas to enhance your family history research. Join us for an hour of engaging discussion that will expand your horizons and revolutionize your approach to uncovering your family’s past.

https://blubrry.com/3738800/136034321/ep12-hollywood-ai-blunder-ai-image-generator-roundup-google-lens-saves-you-time-researching-use-ai-for-translation

Building Better Prompts, Facebook’s LLM May Benefit Family History, MyHeritage Retires an AI Feature

In Episode #9 of The Family History AI Show podcast, Mark Thompson and I begin by exploring the potential benefits of Meta’s open-source approach to AI. Next, we discuss MyHeritage’s plans to retire an AI feature. Then, we review the AI image generation features added to Adobe Illustrator.

In this week’s Tip of the Week, we share valuable insights on crafting effective, hallucination-resistant genealogical AI prompts using the “Role, Task, and Format” prompting method.

The RapidFire segment covers Apple’s AI delays, Google’s impressive math achievements, Reddit’s web crawling restrictions, OpenAI’s venture into AI-based search, and Meta’s groundbreaking image recognition advancements.

In all, this episode offers a blend of practical applications and future possibilities, making it essential listening for genealogists navigating the AI revolution. Whether you’re a tech enthusiast or a family history buff, this show provides the knowledge you need to stay ahead in the rapidly changing world of AI.

https://blubrry.com/3738800/134391782/ep9-building-better-prompts-facebooks-llm-may-benefit-family-history-myheritage-retires-an-ai-feature

Episode 8: Save Time by Summarizing, Meta’s Game-Changing AI Upgrade, FamilySearch’s Summarization Feature, Is the AI Bubble About to Burst?

Hello friends,

Today, Mark and I released Episode 8 of The Family History AI Show podcast. A description of the show is below. But I wanted to take a quick moment to point out how we have structured the show as a way to highlight what we enjoy sharing with you. The show has three parts: 1) In the News, 2) Tip of the Week, and 3) AI RapidFire. The “In the News” block is AI news that genealogists can use–today; these stories cover practical and actionable AI developments that family historians can put to use right now. For example, this week we cover a great summarization feature that FamilySearch quietly incorporated into their groundbreaking AI Labs “Full-Text Search” Experiment. Our middle block, “Tip of the Week,” is a teaching segment where we introduce, explain, and discuss both basic and advanced AI genealogy skills. This week we continue a series on the basics of building genealogy prompts, focusing on one of the fundamental strengths of language models, summarization. Our closing block, “AI RapidFire,” is a glimpse into the future, covering AI announcements, news, and demonstrations to keep an eye on, i.e., advances that–while perhaps not actionable today–seem likely to Mark and I to hold significant potential for the seasons ahead.

After our tenth episode, we’ll do some evaluation. We would love to hear your feedback. We’re having a blast doing the show, and we’d like to do better by listening to your reactions and suggestions.

Blessings, Steve

PS: PRO TIP: The AI skills we cover in each episode during the “Tip of the Week” segment are, as I like to say, eminently transferable. So regardless of whether you are a professional genealogist, serious enthusiast, or causal hobbyist, these techniques will find immediate usefulness in all your knowledge work. We hope that doctors, lawyers, butchers, bakers, candlestick makers, dentists, architects, and administrative assistants will be empowered to do good work with the lessons we offer here, both at the office and in the family history library, den, kitchen table, or spare room–wherever you do genealogy and other knowledge work.

The Family History AI Show podcast
EP8: Save Time by Summarizing, Meta’s Game-Changing AI Upgrade, FamilySearch’s Summarization Feature, Is the AI Bubble About to Burst?
July 31, 2024

In this week’s episode, hosts Mark Thompson and Steve Little explore Meta AI 3.1’s huge large language model upgrade, as well as FamilySearch’s innovative, AI-based summarization feature. They then address growing concerns about AI hype. In this week’s Tip of the Week, they share their approach for mastering the fine art of summarization, a crucial AI skill for genealogical research. The show rounds off with rapid-fire discussions of Google’s privacy policy update, Apple’s response to accusations made about their training data, and exciting developments in AI-powered education. Whether you’re a tech enthusiast or a family history buff, this episode offers invaluable insights into how AI is revolutionizing genealogy and beyond.

Timestamps:
In the News
01:01 Meta AI 3.1: A Huge Upgrade, and it’s Free!
13:09 FamilySearch’s New AI Summarization Feature
20:16 Addressing AI Hype Concerns

Tip of the Week
24:59 AI Building Blocks: Summarization

AI RapidFire
31:25 Google’s Privacy Policy Update
36:57 Apple’s Response to Training Data Accusations
40:02 Apple vs. Google: Platform Competition Heats Up
44:59 AI in Education: New Developments and Partnerships

https://blubrry.com/3738800/133566876/ep8-save-time-by-summarizing-metas-game-changing-ai-upgrade-familysearchs-summarization-feature-is-the-ai-bubble-about-to-burst

Episode 5: From Global Classrooms to Game-Changing Tools

An example of "Six Minutes Over Silver Bullets" and using an LLM to take a transcript and generate derivative resources (i.e., this post written by Jane, my Claude 3.5 Sonnet model, from the text of episode 5 in about six seconds; PROMPT shown at bottom). - Steve:

Hey genealogy tech enthusiasts! 👋

Ready to dive into the latest AI breakthroughs shaping our family history research? Episode 5 of “The Family History AI Show” is hot off the press, and it’s packed with exciting updates that’ll make your ancestors wish they had these tools! 🧬🔍

🎓 First up, Steve Little takes us behind the scenes of his course “AI Genealogy Seminars: From Basics to Breakthroughs” at the National Genealogical Society’s GRIP 2024 Genealogical Institute. Imagine 60 genealogists achieving “escape velocity” in just five days! It’s not rocket science, but it’s pretty close!

🍎 Apple’s making waves with their focus on privacy in AI, and guess what? The whole industry is taking notice! Mark Thompson and Steve break down how this could shape the future of our research tools.

🤖 Hold onto your family trees, because Claude 3.5 Sonnet just entered the chat! This new AI model from Anthropic is not just smarter; it’s changing the game for genealogists. Picture this: asking your AI to whip up a robust pedigree chart of George Washington’s family tree in seconds; Steve shares his experience of trying this best-in-class model for the first time while traveling across Virginia. The future is now, folks!

💡 Our “Tip of the Week” will have you rethinking how you use AI. Spoiler alert: It’s all about “Six Minutes Over Silver Bullets.” Small tasks, big time savings!

🌍 Plus, we’re going global! From Ontario to Australia, the AI genealogy revolution is spreading faster than you can say “Great-great-grandmother”!

Don’t miss out on this genealogy gem! Listen now and join the conversation. How are you using AI in your family history research? Share your experiences and let’s learn together!

🎧 Listen to the full episode here: https://blubrry.com/3738800/132906819/ep5-claude-sonnet-35-is-the-best-ai-update-in-months-the-ai-industry-reacts-to-apple-intelligence-ai-highlights-from-grip-genealogy-institute/
#FamilyHistoryAI #GenealogyTech #AIGenealogy

P.S. If this episode leaves you feeling like a time-traveling AI whiz, share it with your genealogy buddies. Let’s build the future of family history together! 🚀📚

P.P.S. Steve’s AI-assistant, Jane 🤖, generated this announcement after being given a copy of the episode transcript and being PROMPTed to “Draft an engaging blog post and newsletter article announcing the release of Episode 5; make it pithy, engaging, friendly, and impactful. Begin by reviewing Best Practices for this type of social media post. Then create a post like that for this episode.” It took Jane, the Claude 3.5 Sonnet model, about six seconds to create this post, which has been left unedited to display the model’s current abilities.

P.P.P.S: Who’s Jane 🤖? Read this profile: https://chatgpt.com/share/c4621874-6b82-470e-b558-3466c3be1b78

NGS AI Genealogy at RootsTech 2024

I’m excited to be attending my first RootsTech. I look forward to meeting in-person friends and colleagues. I will be presenting on Thursday morning, participating as a panelist Thursday afternoon, and spending a lot of time at the NGS booth in the Expo Hall during the whole event. I hope you will stop by and say, “Hello.”

Here is where you can find me:

Presentation: Intro to AI Genealogy: “Five Tools for Your AI Genealogy Toolbox”

8 AM MT, Thursday, In-Person, Ballroom A

Panel: “Ethics in the Family History Community: Town Hall Discussion”

4:30 PM MT, Thursday, In-Person, Ballroom G

Live Q&A: “Learn about the NGS AI Program”

Twice daily at NGS Booth: 10:45 AM MT and 2:30 PM MT, RootsTech Expo Hall: National Genealogical Society

Open GeneaGPT (the community-built genealogy AI tool) has been updated

Open GeneaGPT (the community-built genealogy AI tool) has been updated from version 2 to version 3 as of Monday 22 January 2024. This is a significant update, transforming Open GeneaGPT into a smarter and more engaging companion for exploring family history, making it easier and more enjoyable for everyone. It brings changes like better conversations, more helpful suggestions for next steps, ensuring a friendly and insightful journey into the past.

https://chat.openai.com/g/g-6YvB8obZp-open-geneagpt

OpenAI’s custom GPTs are amazing tools for creating specialized bots that can perform various tasks, such as extracting data; describing documents, images, records; generating reports, stories, images; and much, much more. These GPTs are tools for the way you work; you build the AI tool you need, or find one on the store shelf. I have been exploring genealogy prompt engineering over the past year, building genealogy GPTs since November, and I have learned a lot about how to create and use them effectively. Recently, OpenAI launched their GPT Store, where users can share their custom GPTs with other ChatGPT Plus subscribers. This is a great opportunity to discover new bots and learn from others. I have shared five or six of my custom genealogy GPTs in the store, which are related to family history research (more are being finished in the lab). Custom GPTs are available to ChatGPT Plus subscribers ($20/month) for no additional cost in the ChatGPT Store.

These are the kinds of genealogy AI tools that I teach students to create; no programming skills are necessary. ChatGPT can interview you, to ask you what kind of AI tool you’d like to create. Then I can show you how to fine-tune the tool to suit your exact genealogy workflow. It won’t fetch you a Snickers Bar or promise to solve a 120-year family history mystery, but within the realm of what large language models can do today, this one does okay.

If you’d like hands-on, step-by-step instruction on how to build your own custom GPTs and other specialized genealogy AI tools, your own flock of bots, the National Genealogical Society is now enrolling for Prompt Engineering and Specialized AI Tools for Genealogists, which starts at the end of January 2024; six hours of instruction over four weeks is just the start; also includes a collaborative study group, sharing successes and learning from failures. The first section of 50 seats sold-out in days, so a second section has been opened. Learn more here:
https://www.ngsgenealogy.org/ai/

Can ChatGPT Help with Genealogy Citations?

This article originally appeared on FamilyLocket.com. See https://familylocket.com/can-chatgpt-help-with-genealogy-citations/

If you’re curious about how artificial intelligence (AI) might help you become more efficient, consider experimenting with citations. The large language models (LLMs) that have become popular in the last year might prove useful in this area. I’ve been using ChatGPT to experiment with AI in the last month as a student in the National Genealogical Society (NGS) course, Empowering Genealogists with Artificial Intelligence taught by Steve Little. Steve has a great blog here: https://aigenealogyinsights.com/. In the NGS course, we had four sessions about the four main LLM transformations: summarize, extract, generate, and translate. Today I experimented with having ChatGPT help me generate citations.

Book Citation

When learning how to create citations, it’s a good idea to start with a basic book citation. The principles for citing books are carried over to citing other publications in genealogy research, like websites. For genealogy citations, we use the Evidence Explained (EE) style. This style is based on the Chicago Manual’s Humanities Style (as opposed to its author-date style). The format for a book citation is the same in both EE and Chicago.

I asked ChatGPT 4 to help me cite a book in Chicago format. It then provided me both the format for a bibliographic entry and the footnote/endnote. Here’s the full response:

To cite the book “Research Like a Pro: A Genealogist’s Guide” by Diana Elder and Nicole Dyer in Chicago format, you would generally use the following structure:

Bibliography Entry: Elder, Diana, and Nicole Dyer. Research Like a Pro: A Genealogist’s Guide. [Place of Publication]: [Publisher], [Year of Publication].

Footnote/Endnote:

Diana Elder and Nicole Dyer, Research Like a Pro: A Genealogist’s Guide ([Place of Publication]: [Publisher], [Year of Publication]), [Page number].

In these citations, replace [Place of Publication], [Publisher], [Year of Publication], and [Page number] with the appropriate information from the book. The page number is only necessary in the footnote or endnote and should correspond to the specific part of the book you are referencing.

It’s important to note that the title of the book is italicized in both the bibliography and the notes. Additionally, in the notes, only the first author’s last name is listed first, followed by the first name, while the second author’s name is in the standard format.

Next I asked it how to create a shortened version of the reference note for use as a subsequent note. Here’s the response:

For a shortened version of the reference note for “Research Like a Pro: A Genealogist’s Guide” by Diana Elder and Nicole Dyer, used in subsequent notes in Chicago format, you would generally include just the primary author’s last name, a shortened version of the title, and the page number being referenced. It would look like this:

Elder and Dyer, Research Like a Pro, [Page number].

For instance, if you are referencing page 45 in a subsequent note, it would be:

Elder and Dyer, Research Like a Pro, 45.

This shortened format is used after the first full citation of the work in your footnotes or endnotes to make subsequent references more concise.

Read the full conversation here: https://chat.openai.com/share/b9d6ddfe-96f3-4881-a75b-2e523a32aa50

ChatGPT did a great job with providing the accurate format for a Chicago book citation. The Chicago Manual of Style, 17th ed., gives the same format on p. 799, section 14.101.

Census Citation

I asked ChatGPT to create a census citation. I started with a citation that I had already made for myself for my ancestor, Eliza Ann Isenhour. I separated the citation I had previously made into multiple lines, removed the punctuation, added an extra word (webpage near accessed) and put the civil division into the same line as the county and state – just to see if it knew where to put that. Here’s my prompt:

You are an expert genealogist. Make a citation for Eliza Isenhour on the 1850 census following the Evidence Explained style manual used by genealogists. Here is the information about Eliza’s enumeration:

1850 U.S. census
Polk, Montgomery County, Arkansas
population schedule
p. 405a
dwelling 6
family 6
Eliza Ann Isenhour in Barnet Isenhour household
database with images
Ancestry
https://www.ancestry.com/discoveryui-content/view/9812411:8054
webpage accessed 17 November 2023
citing NARA microfilm publication M432, roll 28

The response:

To create a citation for Eliza Isenhour in the 1850 U.S. Census following the Evidence Explained style, you would structure it like this:

“1850 U.S. census, Montgomery County, Arkansas, Polk, population schedule, p. 405a, dwelling 6, family 6, Eliza Ann Isenhour in Barnet Isenhour household; database with images, Ancestry (https://www.ancestry.com/discoveryui-content/view/9812411:8054 : accessed 17 November 2023); citing NARA microfilm publication M432, roll 28.”

This citation follows the general format recommended by the Evidence Explained style guide, which includes the year and type of record, geographic location, specific details of where the record is found (page, dwelling, family), the individual’s name and household context, the database and its URL, the date of access, and the specific archival reference (NARA microfilm publication and roll number).

I was pretty impressed! It got almost everything right. This citation is usable. It did not place Polk, the civil division, in the correct position according to Evidence Explained, 3rd ed., p. 237. The civil division should follow the words “population schedule.” I prompted ChatGPT to put Polk where it belongs, and it did. I then asked it to make a few other tweaks, like removing the a after 405a, which is the page number given in the source information from Ancestry, and asked it to add the word (stamped) after 405. Then I asked it to italicize the publication website, Ancestry.

Read the full conversation here: https://chat.openai.com/share/9fa169e8-648a-40e7-bea6-5ff6361411e2

Checking Suggested Citations

It’s important to check for accuracy while ChatGPT is still evolving. Because LLMs aren’t search engines, they sometimes produce incorrect information, according to what it thinks you want to hear. When I asked ChatGPT to make a citation for Eliza Ann Isenhour on the 1850 census, without providing the details from her actual household, it suggested that I follow this format:

“1850 United States Federal Census, [State], [County], [Township or City], enumeration district [ED], page [Page Number], dwelling [Dwelling Number], family [Family Number], Eliza Isenhour; digital image, [Name of Database or Collection] ([URL of the database] : accessed [Date of Access]); citing National Archives and Records Administration microfilm [Microfilm Number].”

This is an okay suggestion, and I love that it created a template that you can fill in. However, it incorrectly tells you to include the enumeration district (ED). EDs were not used until the 1880 census. Read the full conversation here: https://chat.openai.com/share/b7638e29-d6f9-431f-85a9-d2a008ebeb7d

Why do LLMs produce incorrect suggestions? The GPT in ChatGPT stands for Generative Pre-trained Transformer. The AI has been trained by reading a lot of content and is best suited for helping you with creative tasks or helping you summarize a block of text that you provide. The way it works is by predicting what usually comes next when talking about specific topics. So, if you provide ChatGPT with the way you like your citations to look, then give it some information to use, it can probably help with that. While we’re still learning the capabilities of ChatGPT and other LLMs, it’s important to check their work. This will help you know if you can use it for the tasks that will help make your work more efficient.

Shortening Citations

Another usage you might try for ChatGPT and citations is asking it to shorten a citation you’ve already made, when you want to use it for a subsequent note. I returned to my first conversation with ChatGPT about creating a citation for Eliza Isenhour where I provided the details. After the full reference note citation was tweaked the way I like it, I asked it to shorten the citation for a subsequent note. Here’s the response:

For a subsequent note, a short form citation for Eliza Isenhour in the 1850 census can be created as follows:

“1850 U.S. census, Montgomery Co., Ark., Polk, p. 405 (stamped), Eliza Ann Isenhour.”

In this short form citation, the details are condensed, providing just enough information to identify the specific record without repeating all the information from the full citation. It includes the year, the abbreviated state and county, the civil division, page number, and the name of the individual.

My response:

Please include population schedule, abbreviated, and the dwelling and family numbers, which can also be abbreviated.

ChatGPT’s response:

Certainly! Here’s the revised short form citation including the requested elements:

“1850 U.S. census, Montgomery Co., Ark., pop. sch., Polk, p. 405 (stamped), dwl. 6, fam. 6, Eliza Ann Isenhour.”

In this version, “population schedule” is abbreviated as “pop. sch.,” and “dwelling” and “family” are abbreviated as “dwl.” and “fam.,” respectively. This format maintains the necessary details while being concise for a subsequent note.

This can be a starting point for helping you figure out how you want to shorten citations for subsequent notes in a particular piece of genealogical writing that you’re creating.

Conclusion

It seems possible that LLMs could help us start drafting our citations. However, without me providing the details for the 1850 census that I already knew would be helpful, it had a much harder time. Maybe we can train our chatbots to give us citations in the format we prefer after providing them with additional examples and training.

The book citation was great, so using ChatGPT for help citing common source types, like books and articles online, is a great usage right now.

Your Turn

If you experiment with asking ChatGPT to create a citation for you, share below in the comments how it turned out. Was the citation formatted the way you’d expect according to the style manual?

Note: If you are sharing any private information as you practice making citations, turn off your chat history so it’s not seen by the engineers training the chatbot. See https://help.openai.com/en/articles/7730893-data-controls-faq for more info.

More AI and Genealogy Resources

Bettinger, Blaine.”Unlocking Family Secrets with AI | Findmypast,” 22 March 2023. YouTube. https://www.youtube.com/watch?v=exepLKC72Ts. This webinar is a great introduction to LLMs and Artificial Intelligence for genealogy and covers the purpose of LLMs, what they can do, and what they can’t do.

——. “10 ChatGPT Prompts Every Genealogist Needs to Know | Findmypast,” 10 May 2023. YouTube. https://www.youtube.com/watch?v=EbRXzd2SmNM.This gives some great ideas for how to use ChatGPT in genealogy.

Little, Steve. “Empowering Genealogists with Artificial Intelligence 6 September 2023.” YouTube. https://www.youtube.com/watch?v=npQaRJbzE1s. This is an overview of AI for genealogy and some of the capabilities of ChatGPT.

——. “Artificial Intelligence and Genealogy: Using ChatGPT to Write Stories from Family Trees, Create Trees from Stories.” 17 March 2023. AI Genealogy Insights. https://aigenealogyinsights.com/2023/03/17/artificial-intelligence-and-genealogy-using-chatgpt-to-write-stories-from-family-trees-create-trees-from-stories/. This blog post discusses using ChatGPT to help create reports with citations and mentions the style guides used by genealogists.

This article originally appeared on FamilyLocket.com. See https://familylocket.com/can-chatgpt-help-with-genealogy-citations/

New Use Case: Handwriting Recognition to Structured Data

ChatGPT with Vision (GPT-4V) analyzes a handwritten WWII draft card, and not only reads handwriting correctly but also accurately identifies text fields (name, address, next of kin, date of birth, occupation, etc.). This draft card, from my maternal grandfather Dean Lawrence (1921-2003) was chosen for the average block print handwriting; testing will continue to determine how good GPT-4V is with recognizing cursive handwriting, but it appears to handle average print well. Again, though, the innovation is that the AI will correctly label the data; that is, earlier OCR can process simple block handwriting, but it couldn’t tell you whether the text was name, address, or occupation. ChatGPT with Vision (GPT-4V) correctly labels the data. Now, imagine a simple Python script that processes a folder of 20 or 200 or 2000 images like this for you; that will be a trivial task once OpenAI makes API access available for GPT-4V, which is expected (more simply, that is, with middle-school programming skills, tasks such as these will be quickly and easily automated).

PROMPT: You are a professional genealogist; your area of expertise is documents and records; you are adept at extracting every piece of information from a document or record. You are also a skilled writer and image analyst. Think now about a World War II Draft Registration Card, also called DDS Form 1: list every conceivable piece of information that might be found on a draft card (focus especially on names, relationships, dates, places, events, and facts).

Then, find attached a draft card. Extract every piece of information from the image of the draft card.

Finally, create a biographical narrative report from the text on the draft card; dry recitation, no editorializing.

A couple of points to highlight:

you can assign multiple roles simultaneously to the AI: you can prompt the AI to act not only as an expert genealogist, but at the same time to act as a skilled writer and image analysist.
you can ask for several tasks, essentially stepping ChatGPT through a process.
you can ask for a narrative summary of the text in the image, e.g., “create a biographical narrative report from the text on the draft card; dry recitation, no editorializing.”

Here was the response:

RESPONSE:

Information Extracted from the Attached Draft Card:
1.	Serial Number: 234
2.	Full name of the registrant: Warren Dean Lawrence
3.	Place of residence: West Jefferson, Ashe, NC
4.	Mailing address: Same as residence
5.	Telephone number: Not provided on this card
6.	Age in years: 20
7.	Date of Birth: May 21, 1921
8.	Place of Birth: West Jefferson, USA
9.	Name and address of someone who will always know the registrant's address: Mrs. Warren Dean Lawrence, West Jefferson, NC
10.	Employer's name and address: Partially illegible but appears to reference a mining company
11.	Place of employment or business: West Jefferson, Ashe, NC
12.	Signature of the registrant: Appears to be "Dean Lawrence" or a similar variant
13.	Date of registration: Not clearly visible on this card

Biographical Narrative Report:
Warren Dean Lawrence, residing in West Jefferson, located in Ashe County, North Carolina, registered for the World War II draft. Born on May 21, 1921, in West Jefferson, USA, he was 20 years old at the time of registration. His mailing address was the same as his place of residence. The individual who would always be aware of Warren's address was Mrs. Warren Dean Lawrence, also of West Jefferson. Warren's employment details reference what appears to be a mining company located in West Jefferson, Ashe, North Carolina. The draft card carries what seems to be his signature, "Dean Lawrence" or a similar variant.

Prompt Chain to process data further

Once we have the “Information Extracted from the Attached Draft Card,” that information can be standardized, so that if you have many sources of this type (in this example, a draft card), the data can be collected, compiled, compared, and analyzed. For example, if you had 20 of these cards, you may wish to move that extracted data into a spreadsheet or database. Saving the data for each record as a CSV (Comma Separated File, a widely-used file format) file allows us to do this simple task. In the instance, I followed-up the first prompt with a second prompt; using the results of one task as the input for a subsequent task is called prompt chaining. Here was my second prompt:

PROMPT: Create a CSV file from the Information Extracted from the Attached Draft Card. Use the format: "FIELD NAME","VALUE", where FIELD NAME is the field label used in the original image and VALUE is the value extracted from the image, such as "NAME","Warren Dean Lawrence". Display the response in a code window for easy copy-and-paste.

ChatGPT responds with the data in the format of a CSV file, and places that information in a code window, which makes copying-and-pasting easy (just click the “📋 Copy code” icon). One beta mode of ChatGPT, called “Advanced Data Analysis” (formerly “Code Interpreter”), will create an actual CSV file and present you with a download link, but for now we can only use one beta feature at a time; expect that to get better in time.

Up Next: Clean, simple cursive handwriting on a draft card

There remain many document types to test. I’ve been testing more challenging samples to discover where the limit of ChatGPT’s handwriting recognition. Up next is a clean, simple cursive script on a form such as this draft card. Ultimately, however, we will test handwritten documents such as letters, diaries, journals, court orders, and probate files. Handwriting recognition is hard, so I expect the limit might be discovered sooner than anticipated, for the time being.

For the record, here is a screenshot of the beginning of this ChatGPT conversation: