On Thursday 5 December 2024, the creators of ChatGPT kicked-off their “Twelve Days of OpenAI” by releasing the full version of their “reasoning” model, named “o1.” Teased and expected for months, the reasoning model was known by the codename “Strawberry” since spring 2024, and a weaker version, “o1-preview,” had been accessible to paid ChatGPT Plus subscribers for a couple of months. Writing about “Strawberry/o1-preview” in September, Prof Ethan Mollick explains that these reasoning models solve complex problems by planning and iterating, excelling in science and logic tasks.
As an experiment, I asked o1 to craft a research plan. My PROMPT had several components: to provide background for the context window (the model’s “short-term memory” which functions like the setting of a painting), I requested the model review and summarize the GPS and best practices for creating a genealogical research plan; I then provided the model with some factual information from an ongoing project, excerpted from an old blog post.
Here is the full prompt.
PROMPT:
1. Review and summarize the Genealogical Proof Standard.
2. Review and summarize the best practices for crafting a genealogical research plan.
3. Craft a genealogical research plan for the first case mentioned in this post excerpt:
<post>
I have two possible research objectives I am considering for my focus in this course, one modest, the other perhaps too ambitious. Both possible objectives are to confirm or refute the parentage of an ancestor using DNA analysis and documentary evidence. The more ambitious case dates to the late 1700s, involving my 3rd great-grandfather, Isaac Little (1799 — 1884, Ashe, NC) and determining Isaac’s father from among two brothers (Edmund Little or Peter Little) or perhaps their father, Charles Little (a 111-marker Y-DNA test strongly suggests that Isaac and this researcher are descendants of Charles’s ancestor, Abraham Little [1677, England — 1724, Virginia], mentioned above as my surname immigrant ancestor).
</post>NOTE: My usual practice is to “chat with your chatbot,” that is, to iterate through a conversation with a language model to develop best response. But for this experiment, I wanted to see the model’s first, initial effort. You can judge for yourself below. And for comparison, you can evaluate o1’s response below to the relatively paltry response to the same prompt by the legacy model GPT-4.
When evaluating LLM responses, Prof Mollick suggests we ask, how does this response compare to: 1) the best human expert; 2) the average human worker; and 3) the average person; applying that rubric here, we might ask, how does this response compare to: 1) the best genealogist alive; 2) the average family historian; and 3) the average woman or man on the street.
The question I’d suggest asking, when evaluating this response, is: How long were you doing genealogy before you could write a research plan of this sort, given, say, 90 minutes (not just the 90 seconds it took o1).
ChatGPT was released in November 2022; in a manner of speaking, a two-year-old crafted this research plan. Can you imagine what a four-, seven-, or ten-year-old AI will be able to do? I can’t.
The reasoning model generated the response below. You can see the actual ChatGPT session here: https://chatgpt.com/share/67526ede-29fc-8004-87e7-227a5d70cfe6.
Genealogical Research Plan Generated by OpenAI’s First Full “Reasoning” Model, o1
Crafting a Genealogical Research Plan for Isaac Little (1799–1884, Ashe County, NC)
Research Objective:
Determine the paternity of Isaac Little (1799–1884) by confirming or refuting whether his father was Edmund Little, Peter Little, or possibly their father Charles Little. Utilize both documentary evidence and DNA analysis to strengthen or clarify the conclusion.
Background and Known Information:
- Known Ancestor: Isaac Little (1799–1884), resided in Ashe County, North Carolina.
- Timeframe: Late 1700s to early 1800s. Isaac’s birth around the turn of the century places the possible father’s generation in the late 1700s.
- Potential Fathers: Brothers Edmund Little, Peter Little, or their father Charles Little.
- DNA Context: A 111-marker Y-DNA test strongly suggests descent from Abraham Little (1677, England—1724, Virginia), an ancestor to Charles Little and presumably to his descendants. This narrows the paternal line to the Little family in question, but does not directly distinguish among Edmund, Peter, or Charles as Isaac’s father.
Step-by-Step Research Plan:
- Clarify Lineage and Construct a Preliminary Family Tree:
- Assemble a family group chart for Abraham Little and his descendants, with special attention to Charles Little and his sons.
- Document all known children of Charles Little (including Edmund and Peter), their dates, and residences.
- Note any known siblings of Isaac Little and their records to see if patterns of association might emerge.
- Documentary Evidence Search:
- Vital and Church Records:
- Search for birth, baptism, or early church records in Ashe County and surrounding areas to identify any record referencing Isaac Little’s parents.
- Check local church minute books or membership rolls circa 1790–1820 for mention of Charles, Edmund, or Peter Little and their families.
- Land and Property Records:
- Examine Ashe County (or predecessor counties) deeds and land grants. Look for transactions involving Charles, Edmund, or Peter Little, and note any references to Isaac (for instance, if Isaac inherited land or served as a witness to a deed involving a likely father).
- Consider whether Isaac occupied or sold family land, which may indicate inheritance patterns.
- Tax Lists and Early Census Records:
- Review pre-1850 censuses and tax lists to identify household compositions of Charles, Edmund, and Peter Little. While pre-1850 censuses only list heads of households, patterns in the ages and sexes of household members might help locate Isaac as a minor in the correct household.
- Identify continuous proximity of Isaac to either Edmund, Peter, or their heirs in later tax lists, which may suggest familial ties.
- Probate and Wills:
- Investigate wills, estates, and probate files of Charles, Edmund, and Peter Little. If any left wills, did they name a son Isaac? If not named, can any estate distributions or guardianship records hint at an informal acknowledgment of Isaac as a son or ward?
- Check guardianship records if Isaac was underage at the time of a father’s death.
- Court and Legal Records:
- Look for lawsuits, disputes, or indenture bonds that might mention Isaac in relation to Edmund, Peter, or Charles.
- Petitions, bastardy bonds (if that was a legal practice in that region), or other legal documents may provide parental clues if Isaac’s legitimacy or guardianship was ever at issue.
- Local Histories and Published Family Genealogies:
- Review county histories, local biographical sketches, and published genealogies or family histories for the Little family. Although secondary, they may provide leads or references to original documents.
- DNA Analysis and Correlation:
- Refine Y-DNA Matching:
- Work with known Y-DNA matches who descend from Abraham Little lines. Identify matches known to descend from Edmund, Peter, or Charles’s other sons.
- Compare genetic distance, shared marker mutations, and Time to Most Recent Common Ancestor (TMRCA) estimates among these match groups.
- Autosomal DNA Testing (If Available):
- Explore autosomal DNA segments shared with documented descendants of Edmund or Peter Little. Segment triangulation may help determine which branch of the family Isaac is more closely aligned with.
- If possible, identify known living descendants of Edmund and Peter, and compare autosomal matches to see if Isaac’s descendants share more significant DNA segments with one branch over the other.
- Refine Y-DNA Matching:
- Synthesis and Analysis:
- Correlate the DNA evidence with documentary findings. For example, if probate records exclude Isaac from Edmund’s heirs but do not exclude him from Peter’s, and DNA evidence strongly points to Peter’s line, this combination strengthens that hypothesis.
- Consider any conflicting evidence. If a deed suggests one paternity while DNA points another way, delve deeper into the records (perhaps the deed involved a different Isaac Little, or there were naming conventions that caused confusion).
- Conclusion Draft:
- As information emerges, draft a written analysis showing why the available evidence supports one particular paternal identity over the others.
- Cite all sources used and explain the reasoning process in accordance with the Genealogical Proof Standard.
- If the conclusion remains tentative, identify what further records or DNA tests might resolve lingering doubts.
- Iterative Revisions:
- Be prepared to adjust the plan as new findings surface. If a critical record type (like a surviving will or a set of church registers) comes to light, incorporate it and reassess earlier conclusions.
I wanted to share this with you as soon as possible, so I have not critiqued this response with a fine-toothed comb, but I’ll make note of a few quick observations:
- I was pleased to see that the model credited the Board of Certified Genealogists in the first sentence of its review of the Genealogical Proof Standard; earlier models frequently skipped attribution.
- The model seemed to do okay with organization and clarity, suggesting sources, integration of DNA and documentary evidence, and adherence to the GPS.
- The model could have done better with considering a wider geographical scope, prioritizing tasks (perhaps addressing probate and land records before tackling DNA segment triangulation), saying more about socio-historic contextual research, and addressing the limits of autosomal DNA at this generational distance.
Not too shabby for a two-year-old, though.
This was just Day One of the Twelve Days of OpenAI, so there will be more to come this holiday season.
Episode #19 of The Family History AI Show podcast is out now; in that episode, my co-host, Mark Thompson, and I discuss the top five AI breakthroughs for genealogists in 2024. And we just recorded Episode #20 a few hours ago and we talk about reasoning models and the release of full o1, so look for that around the middle of next week.
If something big happens during these Twelve Days of OpenAI, we may do our first “emergency” podcast 😉. I don’t expect Orion/GPT-5 to drop this month, but if something like GPT-4.5, Sora (video generation), improved image generation and analysis (HTR!), and/or an OpenAI web browser were to be released, that would be a nice holiday treat.
