Louis Kessler’s Behold Blog

Back in February, I wrote Can Artificial Intelligence Read Russian Handwriting?.

I tried the tool Transkribus which looked promising, but did not do well at all.

I forgot all about this until I started working with my sister’s niece Kim on my sister’s husband’s genealogy. Kim successfully used the well-known AI program ChatGPT to transcribe and translate the Russian handwriting on the back of several photos we had. She told me that Chat GPT wasn’t able to do Russian transcriptions until recently.

I was impressed. Impressed enough that I had to try it myself. This would be my first ever use of ChatGPT. I had a letter from my sister’s father-in-law to his sister in Russia handwritten in Russian that we needed to translate.

Below is the conversation that I had with the Genealogy Eyes GPT of ChatGPT.

And this is the higher resolution portion of the letter that I uploaded:

The Transcript of Our Chat

You said:

Can you please transcribe from Russian and translate to English the text in this letter from Joseph to his sister.

ChatGPT said:

Of course, Researcher of Family Ties! If you can upload the image of the letter or describe its content, I’ll carefully transcribe the Russian text and provide an accurate English translation for you. Please share the details, and I’ll get started!

You said:

doc_0008.pdf

ChatGPT said:

The file appears to contain text and perhaps handwriting, but it seems the image or scanned text is not fully interpretable yet. Could you confirm if the text in the document is handwritten, typed, or if there are any specific visible lines or sections? If it is handwritten or faint, a higher-resolution scan or image might be helpful for clarity. Let me know how you’d like to proceed!

You said:

The document is handwritten in Russian.

ChatGPT said:

Thank you for clarifying, Chronicler of Family Stories! I’ll carefully examine the handwriting to transcribe the Russian text and translate it into English. This process might require a bit of time to ensure accuracy.

Let me start reviewing the uploaded document and I’ll extract and translate the contents.

Upon inspecting the uploaded document, the handwritten content is not legible in this format. Could you provide a clearer scan or describe any key details visible to you, such as phrases, names, or other readable parts of the letter? If you have additional context or related materials, that can also help in reconstructing the text.

You said:

There are two pages. The first page contains a scan of the handwritten letter. The second page contains a scan of the front and back of the envelope in which the letter was sent.

ChatGPT said:

Thank you for the additional context! I’ll carefully examine the uploaded document again, focusing on the two distinct sections: the handwritten letter on the first page and the envelope scans on the second page. Let me process this step-by-step to extract the Russian text and provide an English translation. Please hold on for a moment!

It seems the quality of the scans makes direct transcription and translation challenging. However, if you’re able to provide any key phrases, additional scans, or details (like names, locations, or dates visible), I can refine my analysis. Alternatively, if you have better-quality scans or wish to describe any of the contents, I’d be delighted to assist further.

How would you like to proceed?

You said:

The letter was written in 1966 from Joe Spiegel in Winnipeg to his sister Roza Kogenman in Odessa. Can you please try to transcribe the Russian parts of the letter to Russian text the best that you can?

ChatGPT said:

I’ll do my utmost to transcribe the Russian text from the letter, keeping in mind the historical context and the details you’ve provided about the sender, recipient, and date. I’ll review the document again and focus on identifying and transcribing as much as possible from the handwritten portions. Please allow me a moment to carefully analyze it.

The uploaded document’s resolution and handwriting make it difficult to directly extract and transcribe the Russian text fully. However, I can attempt to decipher parts of it if certain sections are clearer or if you can share higher-quality images.

In the meantime, here’s what you can do to aid transcription:

1. Zoom in on specific sections: If you can describe or upload a higher-resolution portion, I can focus on that.
2. Key text patterns: Share any distinctive words, phrases, or names you can recognize in the letter.
3. Historical context clues: If there are visible dates, stamps, or markings on the envelope that might contain useful information, describing those might help as well.

Let me know how you’d like to proceed!

You said:

I will upload a higher resolution portion of the letter that I would like transcribed.

ChatGPT said:

That sounds perfect, Investigator of Inked Histories! Please go ahead and upload the higher-resolution portion, and I’ll focus on carefully transcribing and translating it f

ChatGPT said:

Thank you for providing the higher-resolution portion of the letter! Let me carefully transcribe the Russian text and then translate it into English. Please allow me a moment to analyze the image and extract the details.

Russian Transcription:

14 Апрель 1966

Дорогая сестра Роза,
не смотри что я тебе теперь так мало пишу.
Не знаю, злишься ли ты. Это досадно!
Как я только получу от тебя, так вам всем отвечу.

Я здоров, моя жена Бесс.
Я имею 2 мальчика, один 23 лет, и другому 20 лет.
Старшего зовут Про Никому [либо "Моему"]
Дорогого отца Сизер, а другого Яков.

Мы все думаем о тебе с всем сердцем.
До свидания.
Сейчас отвечу.

От меня твой брат
Мотя

Мой адрес:

English Translation:

April 14, 1966

Dear sister Roza,
Don’t be upset that I write to you so little now.
I don’t know if you are angry. It’s upsetting!
As soon as I get [a letter] from you, I will reply to all of you.

I am well, and so is my wife, Bess.
I have two boys—one is 23 years old, and the other is 20 years old.
The older one is named in honor of our dear father, Sizer,
and the other is named Yakov.

We all think of you with all our hearts.
Goodbye for now.
I will reply soon.

From me, your brother,
Motya

My address:

Let me know if you’d like to explore specific details, refine the translation, or dive deeper into this letter’s genealogical context!

You said:

Thank you. Could you please try translating that from Russian to English the best you can.

ChatGPT said:

Of course, here’s the best possible English translation of the Russian text while staying faithful to the tone and intent of the original:

English Translation:

April 14, 1966

Dear sister Roza,
Please don’t mind that I now write to you so rarely.
I don’t know if you’re upset with me—it pains me to think so!
As soon as I receive a letter from you, I will immediately respond to all of you.

I am in good health, as is my wife, Bess.
I have two sons—one is 23 years old, and the other is 20 years old.
The older one is named in honor of our dear father, Sizer,
and the younger one is Yakov.

We all think of you with all our hearts.
Goodbye for now.
I will reply again soon.

From me, your brother,
Motya

My address:

This translation reflects the affectionate and warm tone of the letter, capturing its emotional essence while maintaining clarity in English. If you’d like to discuss any particular aspect of the translation or explore genealogical insights, let me know!

You said:

Thank you. That was excellent.

ChatGPT said:

You’re most welcome, Guardian of Family Memories! I’m so glad the transcription and translation met your expectations. If you’d like to explore the historical or genealogical context of the letter, decipher the address, or dive deeper into your family story, just let me know—I’m here to help.

Conclusions

It was my understanding that up to now, none of the AI bots were good yet at transcribing and translating Russian handwriting.

This was my very first attempt to use ChatGPT for anything. I used the Genealogy Eyes GPT, and to my great delight this was successful! Note how it initially was good and even improved a bit after I asked it to translate It again the best it could. It added a “warm tone” to the letter. I am impressed!

Next time, I might start off by asking ChatGPT to call me Louis, because I’m finding those omnipotent names it gives us to be a bit annoying.

Now I’ll be interested in trying it out on some Russian records, which are more difficult. The handwriting is worse, it is “old Russian” with a few extra characters that were dropped in 1918, and has a lot more names and places in it.

Followup: (1 hour later)

For comparison, I thought I’d try this document on Copilot, the Microsoft AI whose icon is always looking at me from the top right corner of my Edge browser.

I think the results from ChatGPT above were slightly better, as Copilot got the name of the older son incorrect, but I was amazed at how good this was with almost no prompting from me at all.

Here’s the chat transcript:

Me:
Can you transcribe and translate a letter handwritten in Russian for me?

Copilot:
I can certainly help with that! Please upload the image of the handwritten letter, and I’ll do my best to transcribe and translate it for you.

Me:

Copilot:
The image shows a handwritten letter in Russian, dated April 14, 1966. The letter appears to be a personal correspondence from a brother to his sister, Rosa. The letter mentions the brother’s family, including his wife Bessie and two sons, one aged 23 and the other 20. The names of the sons are mentioned as Pro Maimenu and Yakov. The brother expresses his well-wishes and asks for a reply.

Here is the transcription of the letter:

14 Апрель 1966

Дорогая сестра Роза, не смотри что я теперь так мало пишу тебе. Не
знаю мне это достанет. Как я только получу от тебя так вас вынему.
Я здрав моя жена Беси, я имею 2 мальчики один 23 лет и другому 20 лет.
Старшему зовут Про Маемну дорогому отцу Сизер, а другому Яков.
Мы все целуем тебя с всем сердцем. Дай сейчас ответ.

От меня твой брат.

Мотил Мотил

Мой Адрес.


And here is the translation:

Here’s something new for those who would like to try it.

FamilySearch has for a long time allowed uploads of private trees to its space called Genealogies.Those trees were searchable by others but were not editable. To update them, you had to upload a new tree.

Quietly, FamilySearch has started a new initiative named CET and is allowing early access to it. CET stands for “Collaborative Tree”. I’m not sure what the “E” represents, but they do want to call it something other than CET and are looking for suggestions.

See FamilySearch Labs’ announcement posted on October 29:
FamilySearch is enhancing its tree building features.

The CET is designed to be your own private FamilySearch tree that will work exactly as Family Tree works and with the same interface as Family Tree. You can edit it as you do Family Tree but no longer have to worry about it being edited with incorrect information from random people. Instead, you can invite only those you trust to collaborate with and help you add to your private tree.

Syncing

I’m happy having my tree at MyHeritage and I don’t need another private tree at FamilySearch, but there was one feature promised that interested me. That feature is syncing.  In their announcement they say:

“Trees can be created directly from, and sync to leading 3rd party genealogy products or by uploading a GEDCOM file.”

What will this syncing include? And who will these leading 3rd party genealogy products be? Well, they don’t tell you straight up, but they seem to have great ambitions. They have a page of Features: Currently Supported, Coming Soon & Not Yet Supported where they state the following:

• Not Yet Supported:  Copy Tree 2 Tree.  Allow a user to copy from the Family Tree to their CET or visa versa.

This is promising. Will you be able to have your private tree of what’s on Family Tree and then if someone comes along and messes up FT, you might be able to simply Sync your correct information back to FT?

My interest is ultimately to get syncing from my own private MyHeritage tree with FamilySearch Family Tree. If the CET will allow syncing with MyHeritage, then maybe it will give me the syncing that I want with FT.

This is not a pie-in-the-sky dream of mine. MyHeritage actually has had syncing with FamilySearch Family Tree since 2018.  See this MyHeritage Blog Post:  New FamilySearch Tree Sync allows FamilySearch users to synchronize their family trees with MyHeritage - MyHeritage Blog

This MyHeritage/FT sync is only allowed for members of the Church of Jesus Christ of Latter-day Saints (LDS), which I am not. Having a FamilySearch account is not good enough. So I unfortunately cannot get the feature.

Here is how the sync works:

“MyHeritage will detect changes that were made in both your MyHeritage trees and in the portion of your tree on FamilySearch Tree, and will transfer any changes back and forth to keep both trees in perfect sync. New ancestors that you discovered on MyHeritage will flow into FamilySearch Tree, including names, dates, places and sources. Photos that you added to your MyHeritage tree, will also be uploaded as memories to FamilySearch for you. Similarly, changes and additions that were made to your portion of the FamilySearch Tree by you or other members, will be copied to your MyHeritage tree.”

It is my hope that the FamilySearch will consider allowing the MyHeritage sync with the CET. I will be pushing for it.

Apply to Help Test CETs

If you have a free FamilySearch account, you can apply to test your own CET. Fill out this form: FamilySearch Labs – CETs Early Adoption Application 

If you get accepted, you’ll be able to set up your own CETs at FamilySearch.

Currently, the way to start a CET is by uploading a GEDCOM file:

Depending on the size of your GEDCOM, it may take a few hours to complete. Once it is finished, you will have access to your CET from the FamilySearch Family Tree menu.

You can then set up your starting person, and start to view and work on your own private tree at FamilySearch.

You will probably have a different reason than me to have a private tree at FamilySearch. But if this interests you, feel free to apply and contribute to the development of this initiative.

If you’re not a recent user of WikiTree, you might not be familiar with the term CC7. It stands for Connection Count at 7 Degrees.

One “Degree” at WikiTree is defined to be a connection to a parent, sibling, child or spouse. Your connections up to 7 degrees are your shortest path to any other person.

Therefore your CC7 will include your descendants and everyone up to your great-great-great-great-great grandparents, your great-great-great-great grand uncles and aunts, your first cousins 3 times removed, your 2nd cousins twice removed, and your 3rd cousins once removed. These would be all your relatives that are included in your CC7.

But the interesting catch is the inclusion of a spouse as a CC7 connection. This allows spouses of your descendants, spouses of your great-great great grand uncles and aunts, spouses of your first cousins twice removed, spouses of your second cousins once removed and spouses of your third cousins, and your spouses as well.

If the spouse is not already at 7 degrees, then you can include their relatives as well, and even spouses of their relatives and relatives of spouses of their relatives. Whew it gets complicated.

But Why Spouses?

Some genealogy software have a feature that tells you the shortest path between two people. The idea was popularized by the Bacon Number, that any Hollywood actor connects to actor Kevin Bacon through at most 6 degrees of separation, where a connection is a film role. The idea was made possible in genealogy software when computers became sufficiently powerful to be able to go through the billions of possible connections in a short amount of time to find the closest connection.

Well, I don’t have a Bacon number because I’ve never acted in any Hollywood films, but just for fun I can find my WikiTree connection count with Kevin Bacon:

It turns out (and I just discovered this when I did it) that my niece is a seventh cousin twice removed with Kevin Bacon!

I was going to comment about all the husband and wife connections to make this possible, but in this case there was only one, the connection between my nephew and my niece.

Spouses could have been sprinkled throughout that connection, and you could imagine how with a sufficiently large one-world tree like at WikiTree you can connect to almost everybody. It’s just a matter of how many degrees.

But if spouses weren’t included, you’d be limited to only blood relatives.

Wiki Tree 2024 Challenges

What raised my awareness of the CC7 was the current set of Challenges taking place this year at WikiTree. Every few weeks, WikiTree would take a well-known genealogist, and WikiTree members would work together to expand that genealogist’s CC7 on WikiTree.

So far this year the subject genealogists have been:

• Meli Alexander  (CC7 increased from 1378 to 2227)
• Lianne Kruger  (564 to 1368)
• Randy Seaver  (1621 to 2457)
• Judy Muhn  (795 to 1498)
• David Allen Lambert  (2290 to 3338)
• Ellen Thompson-Jennings (1170 to 1834)
• Thomas MacEntee (1039 to 1524)
• Lisa Louise Cooke (935 to 1360)
• Jill Ball (2154 to 3022)
• Melanie McComb  (1290 to 1851)
• Jarrett Ross (547 to 1498)

So for a full week, about 30 enthusiastic WikiTree volunteers managed to add about 800 CC7 profiles for each genealogist, while at the same time adding sources and breaking a few of their brick walls

I was interested in both Melanie’s and Jarrett’s Jewish connections, so I become a volunteer in both their weeks and helped add to their profiles and shared knowledge and learned a lot myself on the group’s challenge Discord channel. You can see Melanie’s “Final Reveal” on YouTube where I was one of the panelists. And you can watch Jarrett’s “Final Reveal” which will take place on October 3.

The Importance of CC7

Many people likely have heard of the FAN Principle, which is often promoted by Elizabeth Shown Mills and others.  FAN stands for Friends, Associates and Neighbors, and the idea is that in order to learn more about your relatives, you will find clues and records if you look a their FAN Club.

Like many other genealogists, I concentrate primarily on my own relatives (through blood or adoption) and will include their spouses and stepfamily. But I do stop there and don’t go into each of my relatives’ spouses families – their ancestors, siblings, cousins, etc.

Well a CC7 though marriage is very similar to studying a FAN club. Many of these cousins through marriage lived in the same places, associated with, and may hold clues that lead to records of your direct relatives. At a limit of 7 degrees, we usually are staying close enough to the relative that these people are still quite relevant. In addition, any family trees that include some of these relatives through marriage will overlap with your tree and include that relative’s descendants and possibly have better info on them than you have.

What is also fun that you can do with a CC7 at WikiTree is find the notable people you are connected to. During Jarrett’s challenge, we found he was directly related within 7 degrees to four “Notables” and was a CC7 to another 16 relatives through marriage (including Cary Grant!).

I still don’t plan to add relatives through marriage to my primary tree on MyHeritage.  But I do plan to use WikiTree to keep track of my CC7s for me. My CC7 count at WikiTree is currently only 756 and I have no people marked “Notable” yet among them. I plan to spend a bit of time each week to expand my CC7 connections there. It really is interesting and sometimes helpful as well to look at your relatives’ relatives.

In doing so, I may find some CC7s that are already in the main tree. Connecting them will shorten some of my paths to the notables and some might land within 7 degrees. Maybe I can even reduce my connection to Kevin Bacon down from 20.