In December, I blogged about a creepy AI discovery I had made when testing ChatGPT’s ability to extract and summarize from newspaper articles. Information in the summary was provided by AI that was no where in the articles uploaded. Although errors like this, called hallucinations, are known to happen with this budding tool, the information that AI proved was 100% correct. That’s what made this feel creepy. How did it know more about my family than the articles I entered?!
I’m now enrolled in my second AI for Genealogy class through the National Genealogical Society and my instructor, Steve Little, noted in class this past week that AI was trained by, among other information, through blog posts.
Bingo! That explains how ChatGPT got my correct ancestors to include in the summary as I have blogged extensively about my Leininger and Landfair families.
Since I’ve blogged about my families for years much of my research is available online. I’ve spoken with other family historians who haven’t had as good a result as I have with using AI. Perhaps this is why I’m getting the results that I am.
When the world wide web was in its infancy, I had difficulty with understanding the concept that once something is place there you can’t get rid of it. Sure, websites come and go but the information is still out there if you look hard enough with tools like the Wayback Machine. Personally, I was involved with an educator only web in the early 1990s and on the world wide web since 1995 so my digital footprint is a large size. Who knew that it would be a help to me with the latest technology?!
If AI is not giving you the results you’d like, I’d suggest that you upload the info you’re working with as a pdf when you prompt it. This might also be a good time for you to start blogging about your family. I will be providing more info on how to do that next week. Happy Hunting!
Ahh, the balance of the universe! Maybe it’s just me but I’ve noticed lately that the more that the web grows genealogy sources, the more sources I relied on in the past have disappeared. I’m definitely not a doomsday prophet but I found my experiences yesterday as a wake up call to change some of my practices in the future. If I don’t I’ll be facing disaster someday. Here’s what happened…
I was going back over a line I hadn’t visited in five years. When I do that, I start with my gateway ancestor, in this case, Mary Ann Hollingshead, and I recheck my saved sources. I predominately use Ancestry.com so I click on the Gallery feature and look at the documents I previously uploaded. Then I go to the hints area and look at all that I had saved as “Maybe” or “No.” I always keep the hint setting on but my tree is so large I don’t have time or desire to check every hint that populates. Weekly, as part of my genealogy cleaning chores, I go through any hints that are shown over the previous seven days and just dismiss them. They don’t really go away; they are saved under the individual that the system matched them to. That’s a nice underused feature, I believe, as you can always go through them at your leisure to examine each one closely when you have the time.
Next, I go back to Facts and check the citations that I had linked to the timeline. For sources that I created from outside of Ancestry.com records, I always but the link so that I can easily review the information and note if anything has changed. That’s where I noticed the first of the serious changes to the web.
I went to Francis Hollingshead and was checking the link I had made to FamilySearch.org for England Births and Christenings, 1538-1975. I used to be able to see the actual page of the document but not any longer:
As you can see on the right side above, I must go to the Family History Center to view. Now I wish I had saved every FamilySearch.org document I have ever found and that’s a lot! It never dawned on me that the information would not be readily available from home. All I could think of was Job 1:20 “…The Lord gave and the Lord has taken away…”.
I did notice that some of the documents were available through FindMyPast.com so I could (and will) go there to snip and save them to my Gallery but not all can be found that way, as the one above shows.
As I went farther back on the Hollingshead line I discovered that British History Online now charges for many documents that once were available for free:
Back in the day, they asked for support through a donation but now they have Premium, Gold, 5-year Gold and 10-year Gold access. What I was trying to reach was Gold level. I only needed one document so it wasn’t worth it to me to purchase a subscription. I had saved in my citation a transcript which is fine for my purposes but if I had known it would go away, I would have snipped and saved the original and transcribed under it. Live and Learn!
Yes, I did try the Wayback Machine to see if I could gain access to these docs and the answer is unfortunately, no. For the British History Online document, only once was it saved and that was in 2015 but you had to log in to access. I tried my old log on but it no longer works.
The next issue I discovered was of a document I had saved in my Gallery. I had the page snipped but I had neglected to include the book’s title page. No worries, I thought, as the link was for Internet Archives. Of course, I happened to hit them just as they went down for maintenance so I couldn’t get the information I needed. The book wasn’t available through any of the other online sources so this just required me to wait awhile to get what I needed.
It’s not just older documents that are no long accessible. Google+, which ties to my Blogger account, is disappearing soon. With it goes all of my former reader comments. I’m glad that I save all of my posts to my genealogyatheart.com website so they will still be available but unfortunately, there’s nothing I can do about the comments.
Genealogy is definitely a practice in patience. Sometimes it’s years before you find the record you seek or connect with a long lost relative that holds the key to discovering a generation back. With organizational changes, patience needs to extend to how we save the documents we find at the time we make the discovery. I’m fortunate that there were only a few records I wasn’t able to access in the 18 generations I checked. I’m hopeful, going forward with the procedure changes I plan to implement in my practice, that won’t be an issue again.
UPDATE 23 Feb 2019: I spoke today with a FamilySearch rep at a local genealogist conference I attended. He stated that some of the records are no longer available from home due to copyright agreements with the holders of the original data. He also stated, if you have found yourself having difficulty viewing some of the records online because they become fuzzy, simply record where you are then click out of the database and go back in. When you restart go directly to the record you left off and it should be viewed clearly. If not, you can report it.