Testing MyHeritage Scribe AI: Very Good, Always Double-check

Encouraged by the outstanding results of MyHeritage's Scribe AI when tested by other genealogy bloggers, I began trying this new feature on several different types of images. 

Scribe AI scored 100% in accuracy when transcribing a handwritten note with a distinctive style of cursive, circa 1943. It also scored 100% in accuracy when transcribing the envelope and postmark of that same handwritten note. Surprisingly, Scribe AI had nothing to say about the stamp, which was very visible and would have added to the context and dating, but that's just a nit because the transcription was perfect.

Above, a more difficult challenge: I asked for a transcription and analysis of my great-grandfather's gravestone, which features a good deal of Hebrew writing. I was quite impressed by much of the analysis but still I could see that eyeballs are very much needed as a double-check on accuracy. Here's what Scribe AI said about each element, followed by my personal analysis.

Iconography & symbolism

Scribe AI says: The top center features a circular medallion depicting a building with arched windows, likely representing a 'Beis Medrash' (House of Study) or a synagogue, which signifies the deceased's scholarly contributions and religious devotion. This is directly linked to the text identifying him as an author. Flanking the medallion are ivy leaves, a common funerary symbol representing immortality, eternal life, and undying affection. The bilingual nature of the stone reflects the cultural synthesis of the early 20th-century Jewish immigrant experience in America.

My personal analysis: I believe the stylized M is basically my great-grandpa's initial for his surname, Mahler, not a representation of a synagogue or my ancestor's supposed scholarly contributions. The rest of the AI analysis is fine.

Monument details

Scribe AI says: An upright, rounded-top headstone crafted from coarse-grained grey and pink granite. The stone is in good condition with minor weathering and some chipping along the edges. A modern circular inventory sticker with the letters 'PC' is affixed to the upper right face. The marker features a bilingual inscription in Hebrew and English, with a central decorative medallion and floral motifs.

My personal analysis: This is accurate but could be improved by explaining what the PC sticker means--perpetual care by the cemetery, a paid service.

Location context

Scribe AI says: Jewish cemetery, likely in the New York City metropolitan area (e.g., Mount Zion or Mount Carmel), based on the granite style, the specific scholarly work mentioned, and the bilingual English/Hebrew format typical of that region and era.

My personal analysis: I'm astonished at the accuracy of location, because the cemetery is in fact Mount Zion in Maspeth, New York--indeed the NY metro area. I didn't tell Scribe AI anything about the cemetery or even the gravestone location; it figured this one out all on its own. 

Research suggestions

Scribe AI says: The inscription identifies Meyer Elias Mahler as the author of the book 'Kanaf Renanim' (כנף רננים), a scholarly work on Hebrew cantillation published in 1907. This is a vital clue for researchers; he can be found in rabbinical bibliographies and New York City death records. His father is named as David Akiva. The epitaph mentions a 'beloved husband' and 'dear father,' confirming he was survived by a wife and children. Given the publication of his book in New York, search for census records in Manhattan or Brooklyn around 1900-1910.

My personal analysis: No, the inscription does NOT identify Meyer as the author, only that he is in the lineage of the author--as indicated by the accurate transcription of the Hebrew inscription, below.

Inscription translation

Scribe AI says: Here lies An important man from a distinguished lineage Author of the book 'Kanaf Renanim' R' Meir Eliyahu son of R' David Akiva Born in the year 5616 [1855/56] Passed away 3 Shevat 5670 [January 13, 1910] May his soul be bound in the bond of life

IN MEMORY OF MY BELOVED HUSBAND AND OUR DEAR FATHER MEYER ELIAS MAHLER DIED JAN. 13, 1910 AGED 52 YEARS May he rest in peace

My personal analysis: the translation is accurate, according to the translations I've had done in the past. Meyer is shown as being "from a distinguished lineage" of the author of the book. He did not write the book, as the research suggestions note. 

Highly encouraging, eyeballs always needed

I'm very encouraged by the mainly accurate info! Will be testing Scribe AI more in the coming weeks. I owe it to my relatives and my ancestors to follow the warning that MyHeritage shows at bottom of all these results: These insights were generated by AI and may contain errors. Be sure to review them for accuracy. 

Ancestry "Ideas" in Beta

Ancestry is trying something new, offering AI-generated "ideas" for researching an ancestor on your family tree. If you have this feature, now in beta, it will be on the top menu. Look to the right of the ancestor's name,  next to the search button on that profile. I first noticed it on Wed, Jan 28 (it had disappeared by Sat, Jan 31 but then reappeared on Feb 1).

I tried "Ideas" for several ancestors that I've researched extensively.

As shown above, the "ideas" for my husband's great aunt consisted of (1) search for the marriage record, (2) trace the ancestor's residences, and (3) locate her death cert. 

Since the marriage cert is attached as a source and in the gallery, nothing new there. Since every US Census available for this ancestor is reflected in her profile, nothing new there. Not shown in the image above but on my tree is this ancestor's death cert as a source. Nothing new there.

Interestingly, "ideas" come with the offer of a detailed action plan. At left, an explanation of why a marriage record is important (this example is from a different ancestor) and suggestions for searching for missing marriage records. (This ancestor's marriage record is listed as a source on the profile and the scan of the cert is in the gallery, by the way.)

Ancestry knows the idea to search online for a marriage index is "beginner-friendly" which I suspect is meant to encourage beginners to go ahead and search.

The next two suggestions (look for a county marriage registration and look for local newspaper marriage announcements) are a bit more advanced and clearly good recommendations.

I note that this AI action plan includes the idea to search in FamilySearch, Ancestry, and MyHeritage! Good suggestion.

My initial reaction is that the AI suggestions don't reflect what is attached to a tree and what is missing. Also these ideas are rather basic for someone with a bit of experience. Maybe this feature will be improved as the beta testing continues?

My next step is to test the AI "ideas" feature with ancestors who are not as well documented. Stay tuned!

Do you have Ancestry "ideas" and if so, what do you think?

UPDATE Jan 31: This beta feature was only on one of my three main Ancestry trees. When I turned on my computer today, it had disappeared from that tree and is not yet available on any other tree. 

UPDATE Feb 1: Beta feature "Ideas" reappeared but on a different tree.

Deeply Wrong Results Via AI Deeper Dive

Every year around this time, I redo my research on Leona "Lee" Wallace (1903-1989), who ran the legendary Macy's Thanksgiving Day Parade from the late 1940s until the early 1950s. Lee was born on November 24, 1903 in Poland. She was my aunt Dorothy's life partner and is remembered fondly as a devoted aunt. I really enjoy keeping her memory alive through my role as family historian.

Of course I use genealogy and newspaper sources but I also use a regular ole Google search just in case. And...the online search results were interesting, to say the least.

No relation to the actor Lee Wallace

My initial Google search included the above "AI Overview" of results. It says "Lee Wallace is primarily known as an actor, but there was also a Leona "Lee" Zonna Wallace who, along with her company, helped manage the Macy's Thanksgiving Day parade and its special events." [Correctly, it indicated no info connecting the actor Lee Wallace to this parade, and went on to list some of the actor's film credits.]

OK, the AI results do show "Lee Wallace Associates" which was, in fact, my aunt Lee's company. And there's a distinction in the results between the actor and the person who ran the Thanksgiving Day Parade, also true. Mind you, the info used by Google's AI was directly from my own genealogy blog posts about Lee Wallace Associates. 

Google's AI next asked whether I wanted to take a deeper dive into the AI results. Sure. 

Deeper dive: cue the hallucinations

See the deep-dive results above? The assumption is that Lee Wallace was male. Nope.

Then came fascinating and utterly fanciful hallucinations about Lee Wallace's "portfolio of events." 

Some of the parades and events listed in the so-called results didn't even begin until after my Aunt Lee retired. There is no possible way that Aunt Lee had anything at all to do with the St. Paddy's Parade or the NYC Marathon. Not the Orange Bowl Parade either. Hallucinations!

These deeper dive AI results gave me and my family a big laugh. But no correct or usable info in this case. 

Good news - New news stories!

Anyway, I did find a new (to me) newspaper story about Lee when I searched NewspaperArchive. It was a human interest feature that appeared in late December, 1950 in several Midwest newspapers, about Lee planning the 1951 Macy's Thanksgiving Day parade in New York, also discussing her early working career. A nice new article I hadn't yet uncovered. It's fun to see how far and wide the Macy's parade was known.

Video to Audio to Transcript to Translation via AI

The well-known speaker Thomas MacEntee recently gave a presentation to my local genealogy club about how to use AI. During the Q&A period, I asked him whether AI could translate and transcribe foreign language audio for free. His answer was a definite yes. So this week I began to experiment.

I have a 1998 video interview of my mother's first cousin, Viola, speaking emotionally about her experiences as a Holocaust survivor and her early years with her family. The interview was conducted in Russian in Israel through the USC Shoah Foundation. A decade ago, a friend who knows Russian kindly translated the gist of this video interview. Now I wanted to see what AI could do for me, for free, in better understanding family history comments that Viola made early in the interview. 

Process: video audio to digital audio to transcript

First, I popped the DVD into my player and as soon as the interview began, I started recording a voice memo on my iPhone. My first audio recording was 11 minutes long. This was important because Thomas said that without a paid AI account, it's better to keep projects shorter and simpler to get things done.

Next, I had to change the m4a recording to mp3 format, which I did with a free online converter (I used CloudConvert but there are other sites out there). 

I tried uploading the mp3 to ChatGPT (free version) and asked for a transcription and translation from the Russian. But the AI responded: "It looks like I can’t run Whisper (speech-to-text) directly in this environment, so I can’t transcribe the MP3 automatically here."

So I uploaded the mp3 recording in Russian to TurboScribe (one of many sites that do this) and I asked for a free transcription. I chose the best quality/accuracy and within minutes, I downloaded the written output as a pdf.

Formatted translation from the Russian

Finally, I took the pdf of the Russian transcription and uploaded it to ChaptGPT, explaining a bit about this being an interview. I asked for this transcript to be translated into English and formatted as interviewer and interviewee. 

The AI had no difficulty distinguishing between the words of the person asking the questions and the person answering. It did ask whether I wanted a summary or a complete transcription (I wanted everything). Also it asked whether I wanted some original terminology left as is, with translation in brackets (yes).

ChatGPT finished that initial translation and asked for me to upload more so it could create a single, seamless document. So I went back and recorded 6 more minutes, going through the audio to digital audio to mp3 conversion rigamarole, next getting the free transcription, and then uploading the pdf from this second segment to ChatGPT.

This time, I named Viola as the interviewee and the AI showed her name in front of all of her responses. In the blink of two eyes, the answer showed me both segments compiled into one seamless interview about Viola's mother, father, and grandparents and their life before World War II. The top of page one is shown here.

Output: Formatted to my specs

Chapt GPT preserved some of the original terminology (see image at top, look for the word for tavern) and some of the less distinct words were picked up and translated, too. 

No cut and paste for me. I just asked for a .docx Word document, which was quickly created for easy and free download. The output is in complete sentences, with proper punctuation, a smooth read. I added a note that ChatGPT had created the document and the date. Done!

Use with caution

ChatGPT warns that it can make mistakes (see image here). I also asked it to please delete the file at the end, after I had finished my download.

Given how many steps were needed to go from video interview to final document, there are multiple opportunities for mistakes/omissions/typos to creep in. Very likely there are some nuances that got lost along the way but in the end, I believe this was a successful experiment. Thank you to Thomas MacEntee for the encouragement!

Getting Context from Ancestry's LifeStory with AI Insights

Still in beta testing, AncestryAI is an option to provide historical and social context for some elements of the LifeStory feature on an ancestor's profile page.

Above, the early section of the LifeStory for my great uncle Abraham Berk (1877-1962). This takes the form of a timeline including family events such as his birth and the birth of his siblings, followed by his residential locations in chronological order, marriage, immigration, birth of children, occupation, and actually all events on his profile page.

Next to some of these LifeStory items is an option to Ask AncestryAI about a time and place in the ancestor's life. The AI summary helps add context to the ancestor's background. As shown above, here the AI is explaining what Lithuania was like in 1877, the year of Abraham Berk's birth. 

Other options to learn more about a time and place include what would someone wear to a wedding then, what mourning customs existed then, what was entertainment like then, what local dishes were popular then (see below, about Lancashire's fave foods in 1901).

While much of the AI-generated info is general, it still is a helpful starting point for understanding an ancestor's life and can give clues to fleshing out a bite-sized bio with context. Worth checking out if you have this feature in beta at Ancestry.

Note: Yesterday's blog post looked at FamilySearch's Brief Life History feature. Tomorrow's blog post will look at MyHeritage's AI Biographer feature.

Ancestry's Ask AI Feature

This week, when looking at a German language Hamburg passenger manifest for one of my ancestors, I noticed that Ancestry was offering me the opportunity to explore this document using its Ask AncestryAI feature. Of course I took a look! I haven't tried any Ancestry AI feature before this.

Above, part of the screen, with the AI interpretation on the right and the transcribed record (plus the original image) on the left. The AI seems to have used the info from the record detail and constructed a narrative that began "Bela Roth, a Hungarian male, departed from N. Bereg, Hungary, at the age of 42 on October 17, 1907..." 

The AI named the ship, the ship's ownership, and said he was a merchant (true) and was accompanied by six other household members (true) including his mother (not true) sons (true), and father (not true). The AI concluded by citing the source of this record.

In actuality, Bela was accompanied by his wife and sons, and he named his mother as the nearest relative in place he left. Bela, himself, was the father of the sons.

Deciphering a handwritten manifest is a challenge, and when I don't know the language, it's an even bigger challenge. Here, I had to compare what the AI said to the actual record AND to my family tree to understand what was true and what was not true. Also, the AI had no way of knowing that N. Bereg = Nagy Bereg. But I knew the full place name from prior research. I tried the AI feature on another German-launguage Hamburg passenger manifest, with similarly mixed results. 

I can imagine situations where the AI assist would be helpful. Still, IMHO, there's no substitute for understanding a document's purpose, timing, format, content, and trying to decipher it independently from what the transcription says and what any AI assistance says. I'll continue to test this feature, hoping to learn a few new details--that I'll confirm for myself.

UPDATE: This AI feature is available for a variety of documents. Here's what it told me about a man's WWII draft registration card. I clicked the thumbs down on this description--the man in question did not serve, and the narrative is rather flowery without much substance, unfortunately. Oh, and let me quote the disclaimer from the bottom of the screen: This feature is powered by an AI language model using only information from this record. Responses may be inaccurate. 

Try this feature if you can, and see what happens!