Army Historical Foundation’s Genealogy Seminar

Blog Banner - Army Historical Foundation's Genealogy Seminar

On 11 May 2024 I attended The Army Historical Foundation’s Genealogy Seminar, hosted at the National Museum of the United States Army. The seminar was entitled “Unlock your military legacy.” There were attendees both in person and online, and I was able to attend in person.

The speaker lineup was impressive: Richard G. Sayre, COL (USA-Ret.), Pamela Boyer Sayre, and Rebecca Whitman Koford, CG, CGL. Many of you know Rick and Pam from their outstanding presentations. Among her many accomplishments and extensive service to the genealogical community, Rebecca currently works as Executive Director of the Board for Certification of Genealogists® and is the Director of the Genealogical Institute on Federal Records (Gen-Fed) which is held annually at the National Archives in Washington, D.C.

Rebecca began the seminar with an excellent presentation about “Records of the U.S. Army held by the National Archives and Records Administration.” Sharing her hands-on experience, she demonstrated the types of records and how and where to locate them. Demonstrations of how to use the NARA Catalog are always beneficial. She also shared examples with us of records she had found about her ancestors.

“Map Repositories in the Washington D.C. Area” was next, and in that presentation Rick discussed more than the repositories; he explained the history of mapping in the US. It is significant to know about the maps, including who created them and their purpose. He showed what was on the maps and their usefulness for using them in the context of an ancestor’s war experience. He shared so many great examples!

After a delightful lunch, and having been inspired by the two previous presentations, I was ready for the next presentation. Pam presented “Tracking an Eighteenth or Nineteenth Century Soldier.” She showed us how to time travel using Google Earth Pro. First she demonstrating what could be done, then she explained the steps in detail for how to use those features to document your military ancestor’s life in a visual and engaging format. Not only is this a great way to share information with non-genealogists, but this is also a great technique for immersion into the context of an ancestor’s service. This is something I had been considering, and using her approach will make the task straightforward and manageable.

The last presentation was by Rick and Pam, “Learning About a Twentieth Century Soldier.” This session presented resources and brief case studies about researching the service of twentieth-century soldiers at NARA facilities. Rick and Pam decided to focus on WWI, and a follow-up presentation for learning about WWII soldiers will be recorded and distributed to attendees at a later date. After the resources were discussed, a clear methodology was presented. Of course that methodology included the use of one of my favorite tools, timelines. Rick clearly described the homework that a researcher needs to do before contacting and visiting a NARA facility.

The presentations were very practical in nature. While it is great to find out about resources and how to use them in your research, it is also important to know where and how to find them. Being able to use them and share them is also incredibly valuable. The NARA Catalog can be awkward to navigate, so insights that the speakers shared were appreciated. There are always things to learn from such distinguished genealogists.  

The final presentation held a couple of surprises for me. Two of my books were listed in the bibliography for the final presentation. Of course I was delighted to be included. The real surprise is that Rick and Pam showed a slide that contained the cover of my recent book, “Researching U.S. WWI Military Members, Military Organizations and Overseas Noncombatants: A Research Guide for Historians and Genealogists” I was happy for my book to receive a shout out. (They had no idea I would be in the audience!) I was even happier to see that the Pioneer Infantry Regiments were also mentioned in the presentation. If that was not enough, I was delighted when Rick asked me unexpectedly to say a few words about the Pioneer Infantry Regiments. What a privilege, and how great to see the Pioneers’ stories being told.

This all-star line-up held an informative seminar and disseminated actionable information! Thank you!

In the next blog post I share more about my visit to the Museum after the seminars concluded.

You can find out more about these two books, and others, on this website. They are available on Amazon.

“Researching U.S. WWI Military Members, Military Organizations and Overseas Noncombatants: A Research Guide for Historians and Genealogists”

“A Guide to the U.S. Pioneer infantry Regiments in WWI”

11 covers

Learning About AI

Blog Post Banner - Learning About AI

Have you wanted to learn more about Artificial Intelligence?

Recently I gave a talk about Using AI for Genealogy, and shared some of my sources for education about AI. You can find out more about the talk  and if you want to learn from a genealogist who is a professor with a Ph.D. in Computer Science and Engineering, you might consider having your group book it.

There are many resources available to learn how to get started with generative AI, and some ideas for using it in genealogy. Among them are posts on this blog .

NOTE: DO NOT put any sensitive information into any AI tool.

The first recommendation is a paper that you can download. Genealogists need to learn about prompt engineering to use AI tools effectively. A great paper that offers a catalog of prompt patterns is a good place to start. These prompts presented in the paper are general in nature, but they can be applied to genealogy. The paper is “A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.” It is an academic paper, and they can look intimidating, but they do not have to be! You can copy-and-paste parts of it into ChatGPT (or another text-to-text AI tool) and ask it to create a summary or explain it. My specific advice is to look at the tables labeled “Contextual Statements” to learn the patterns. I actually copied text from these tables, and combined information about the patterns offered by a generative AI to create a personal cheat sheet.

If you want to dig deeper and understand more, you may want to look beyond genealogical applications and learn about the technology. Understanding what the tools are and how they work might help you be more comfortable with using them and applying them in genealogy.

In its “AI Ready” commitment, Amazon Web Services (AWS) has set a goal to train 2 million people. As part of this commitment, AWS offers free courses about AI. These courses are written for all different levels of knowledge. From the AWS webpage describing the commitment, scroll down to the section “Courses for business and nontechnical audiences” where you can follow the links to register for the courses. A free account is needed. “Introduction to Generative Artificial Intelligence” is a good starting point, with simple and understandable explanations and no formal assessments. (That means no tests!)

AWS Courses for business and nontechnical audiences list

If you want to learn in a more structured way, there are online classes available. These are more formal, with structured lessons and activities that you have to turn in. That should not intimidate you, as these courses are designed for beginners who have little or no technical background. The beginner aspect should not dissuade people with more experience, as there is always something to learn in courses like these. I enjoyed the first and simplest course on the list, as well as courses in the series “Generative AU Learning Planning for Decision Makers” and the “Foundations of Prompt Engineering.”

Coursera

Coursera offers “Prompt Engineering for ChatGPT.” It is taught by the professor who wrote the article that I recommended. If you take this course for free, be sure to allocate time for it each week because the course materials are only available to paying participants after the end of the class. I found this to be a very enjoyable course, with the assignments being as simple as using ChatGPT 3.5 to try the patterns from lessons and submitting the prompt and response via a text box.

Coursera Prompt Engineering for ChatGPT image

GALE Courses

Another course that I have begun is “Introduction to Artificial Intelligence” on GALE Courses (formerly known as Learn4Life). GALE Courses may be available from your local library website, or from a neighboring county for free by using a library card they issue. For those in Anne Arundel County, Maryland, you will find GALE Courses offered by the Howard County Public Library, so get a library card from them. (At Howard County Public Library this is the link to the description https://education.gale.com/l-howardmain/online-courses/introduction-to-artificial-intelligence/?tab=detail). These are 6-week courses, organized into two lessons per week, and there are discussion boards and ungraded quizzes. In order to obtain a certificate for this course, you have to pass a final containing multiple choice questions that appears to be based on the ungraded, optional quizzes for each lesson. Check on your library’s website for an alphabetical listing of online resources or contact a librarian.

Howard County Library System GALE Courses Introduction to Artificial Intelligence course

This is a technology course about the science of how a computer can perform tasks that usually require human intelligence. It covers the forms of AI, how AIs learn, AI applications and ethics. It will not be something that you can use immediately for genealogy, but it will give a foundation as we go forward seeing more and more AIs.

No matter how you decide to learn, keep learning!

Let me know how you are learning about AI.

NOTE: I have no affiliation with any of the courses or services in this post.

Shake That Family Tree Event

Blog Post Banner for "Shake That Family Tree" Event

On 14 October 2023 the Howard County Genealogical and Historical Societies and the Howard County Public Library System organized the “Shake That Family Tree” event at the Miller Library in Ellicott City, MD. This was intended as a beginner-level event, but there was certainly great information for all the genealogists who attended.

I was delighted to have been invited to host a table about military research and my books. All day long there were interesting talks, and a room full of tables with representatives from local history and genealogical societies who were eager to share information about what they were doing and offer help to genealogists at all levels.

Many of the people who stopped by did not know if they had ancestors who served in WWI. The best place to check is the FamilySearch database for the VA Master Index, which has been covered in this updated blog’s post “Did My Ancestor Serve in WWI?” to reflect the changed search interface.

The Howard County Genealogical and Historical Societies and the Miller Library hosted a wonderful event, and it is certainly my hope that this might become an annual event!

"Shake That Family Tree" tables

Back to School: Genealogy Style

Blog Post Cover: Back to school genealogy style

When autumn comes, we think of going back to school. Genealogists are always learning, and webinars are a great way to do that. Presentations give us information, introduce us to new techniques or provide a new way of looking at our research. These resources in the blog post offer great classes and more.


The Genealogy Center at the Allen County Public Library hosts the Periodical Source Index (PERSI) and has many recorded webinars available on its YouTube Channel. You can even send them an email if you have a question.

ACPL Genealogy Center Home Page

The Midwest Genealogy Center at Mid-Continent Public Library offers a variety of resources. You can even request an Appointment with a Genealogy Consultant. Be sure to check out their upcoming and register for them on their events page. You can view their recorded talks on their YouTube Channel.

The Midwest Genealogy Center at Mid-Continent Public Library Home Page

BYU’s Harold B. Lee Library offers new webinars every week. They also offer a large library of recorded webinars.

BYU Library Webinar Page

Of course for the more adventurous, consider a class at your local community college.

When everyone around is going back to school, join them!

Artificial Intelligence: Google Bard vs. ChatGPT

Blog Post Banner: Google Bard vs. ChatGPT

It is inevitable that similar AI tools will be compared. This blog post takes a look at comparing OpenAI’s ChatGPT and Google Bard.

When Google Bard was asked how it was different from ChatGPT, it answered that its training data contained images, that it could access the internet, and that it was a more general AI rather than a text-generating AI. Bard also told me that while ChatGPT was creative, it was more creative.

Google Bard has an interesting approach to answering prompts. Unlike ChatGPT, its training and knowledge does not end at 2021. It can go out and get content from the web to generate its answers.

Like ChatGPT, Google Bard can also hallucinate and authoritatively state inaccurate information. The “Google it” button found under a Bard response can help comfort you that the answer is not a hallucination.

These two AI tools do have some differences.

ChatGPT offers multiple conversations so that a user’s conversations can stay organized. It also has the ability to present previous conversations and pick up where it left off. Google Bard holds one conversation. It allows users to return to their previous prompts by selecting their Bard Activity from its menu. The responses to the prompts have to be selected at the time, and cannot be recalled.

Bard responses can contain images returned from the web. The responses, without any images, can be uploaded to a document in the user’s Google Drive or into the text of a gmail. ChatGPT responses are text-only, and need to be copied and pasted from the browser into a document. (Note: browser addons or plugins to capture responses are not discussed in this blog post. Any code you add to your browser this way should be researched thoroughly!)

Given that the content generated by Bard is not owned by the user, I will probably use ChatGPT for generating text and explaining concepts. (Of course, what ChatGPT generates should be verified!) I do prefer that responses are saved, and that different chats can be active.

It is possible that I might lean on Google Bard more for research questions, and will ask Bard for its sources. Undoubtedly the “Google it” button will be used in those efforts.

Of course, we can expect that Google Bard and other AI tools will continue to evolve at a rapid pace.

Based on the versions available at the time of this blog post being written, below is a table comparing features of OpenAI’s ChatGPT and Google Bard that I found notable.

Genealogy and AI: Google Bard

Blog Post banner - Genealogy and AI: Google Bard

Although Google Bard states that it removes personally identifiable information when using conversations to improve the model, DO NOT INCLUDE PERSONAL INFORMATION IN YOUR CHATS.

This week I spent some time working with Google’s challenger to OpenAI’s ChatGPT. Google Bard is a Language Model for Dialogue Applications (LaMDA), and I was working on the day that Bard began to bring images from Google Search into its results. Bard advertises that it helps you plan, solves complicated problems and supports your creative process. When it quotes content, it will cite where it found the material, or the computer code repository that was used.  

In this article you will notice that I do include screenshots of answers, as I did for ChatGPT. That is because Google owns the generated content. If anyone wants to publish the content, they have to get permission from Google; at best Google and the user might share the rights to material. (In comparison, when you generate content in ChatGPT you own the rights to that content.)

Google Bard can be found at: https://bard.google.com.

I also recommend viewing the Frequently Asked Questions.

You can select to save your Bard Activity, but even if that option is deselected, your activity is saved for up to 48 hours so that the feedback can be used. You can also select whether or not your activity is auto-deleted after 18 months. In my Bard Activity I could see the prompts that were given, but could not retrieve Bard’s responses, so remember to SAVE the responses. At the time of your session you can copy-and-paste them into a document or use the upload function described below.  

The menu for Google Bard appears on the left hand side of the window.

At the bottom of each response were buttons to like, dislike, upload the response, or “Google it”

bottom of Google Bard response

When you select to upload a response, you have options to upload it your Google Drive or draft an email in Gmail. The uploaded response will include text but NOT include the images you see in Bard.

Google Bard upload options

I decided to ask some genealogically oriented questions, as I had done when testing ChatGPT.

“What are good resources for genealogy?” The answer to this prompt was a reasonable list of record databases, websites and societies.

“How can you help me with my genealogy?” This prompt was answered with ideas about genealogy research, finding resources, interpreting data and help create a family tree.

“How did someone travel from New York City to Newport, RI, in 1850?” Google Bard answered that the travel would have been by stage coach and steam ship, presenting me with images and data from the web along with its answer.

I asked what its sources were for this information, and it was listed sources. It also shared that it used its own knowledge to fill in the gaps.

When I asked how to find the source material, it provided links to places to buy a physical copy but did not provide a link to the source on Google Books. It did tell me that the book was available to view and download from Google Books. That resource was actually a very interesting discussion on travel to Newport between 1800 and 1850.

Since the user does not own the generated content, and the web is used to help answer prompts, this AI tool may be more useful to me as a research assistant.

You can always give it a try!