Family history in Ashe County, North Carolina
I had an opportunity today to experiment a bit more with using artificial intelligence to create family trees (GEDCOM files) from narrative texts. My goal was to see how much I could limit the AI's creativity to insert information into the GEDCOM file that wasn't in my prompt. (Earlier, I had discovered two constraints that … Continue reading AI Genealogy: Text to GEDCOMs: Surprises, Cautions, Discoveries
I've been an enthusiastic explorer of artificial intelligence-assisted genealogy for the past several months. My 35-plus year interests in linguistics and language, computers and programming, and genealogy and family history converged in November 2022 with the release by OpenAI of ChatGPT to create new possibilities like a supernova creates new elements such as gold, silver, … Continue reading AI Genealogy: Value of Trusted Critics, Skeptics
I enjoyed and recommend yesterday's livestream "Genealogy & AI: Unlocking Family Secrets" by FindMyPast, featuring Jen Baldwin interviewing Blaine Bettinger. The discussion delved into the potential of AI and chatbots like ChatGPT in the field of genealogy. However, as with any powerful tool, there are potential pitfalls that genealogists should be aware of when using … Continue reading AI Genealogy Tip: Don’t Get Burned by Spicy Autocomplete
Highlights: Genealogists can quickly generate a cleaner copy of an old newspaper article (not a perfect final draft) from a messy OCR text dump. A carefully crafted PROMPT found and fixed 49 out of 54 errors in an newspaper OCR article text. NO HALLUCINATIONS were introduced into the response. The AI was limited to processing … Continue reading AI Genealogy Use Case: Cleaning-up OCR Text
How to Extract Information from Text Sources Using Artificial Intelligence Three examples: obituary, wedding announcement, newspaper article After my discoveries last week that ChatGPT (model GPT-4) can: (1) create, read, and correctly interpret GEDCOM files, (2) create narrative reports based only on GEDCOM data, (3) match narrative style to location and setting of text, and … Continue reading AI and Genealogy: Using ChatGPT to Glean Info from Obits, Articles, and Announcements
GPT-4: A Revolutionary Tool for Genealogists and Family Historians Introduction I had fun making a couple of discoveries this week while exploring the new GPT-4. As someone with lifelong interests in the worlds of linguistics, language, computers, programming, writing, storytelling, genealogy, and family history, it has been surreal to see these interests come together, creating … Continue reading Artificial Intelligence and Genealogy: Using ChatGPT to Write Stories from Family Trees, Create Trees from Stories
In my SLIG 2023 class today in Evidenced-Based Writing (Salt Lake Institute of Genealogy), we were in a session on writing preparation and organization, so when we were given ten minutes to try an organizational exercise, I thought I'd see what ChatGPT could do in ten minutes. I've been working on a research project for … Continue reading Genealogical Evidence-based Writing, Organizational Brainstorming, and ChatGPT (OpenAI’s artificial intelligence)
[I took five genetic genealogy courses in 2022, most focused on endogamy, pedigree collapse, and multiple relationships. Nicole Dyer at Family Locket asked me to share something about that. This post focuses on visualizing complex relationships, such as multiple instances of pedigree collapse and multiple relationships in one DNA match (e.g., between two close cousins). … Continue reading Visualizing Complex Relationships: Working with Pedigree Collapse, Multiple Relationships, and Endogamy
Welcome to the site's new home, AsheAncestors.org. I look forward to sharing family history, genealogy, and stories with you using the more robust resources available here. Both new and returning readers are invited and encouraged to subscribe to be notified of new posts.
To narrow the scope of a researcher's task, overlaying an enumeration district map on top of a modern street map may enable the researcher to focus their line-by-line browsing of census page images by dramatically lessening the number of pages to review.