It is inevitable that similar AI tools will be compared. This blog post takes a look at comparing OpenAI’s ChatGPT and Google Bard.
When Google Bard was asked how it was different from ChatGPT, it answered that its training data contained images, that it could access the internet, and that it was a more general AI rather than a text-generating AI. Bard also told me that while ChatGPT was creative, it was more creative.
Google Bard has an interesting approach to answering prompts. Unlike ChatGPT, its training and knowledge does not end at 2021. It can go out and get content from the web to generate its answers.
Like ChatGPT, Google Bard can also hallucinate and authoritatively state inaccurate information. The “Google it” button found under a Bard response can help comfort you that the answer is not a hallucination.
These two AI tools do have some differences.
ChatGPT offers multiple conversations so that a user’s conversations can stay organized. It also has the ability to present previous conversations and pick up where it left off. Google Bard holds one conversation. It allows users to return to their previous prompts by selecting their Bard Activity from its menu. The responses to the prompts have to be selected at the time, and cannot be recalled.
Bard responses can contain images returned from the web. The responses, without any images, can be uploaded to a document in the user’s Google Drive or into the text of a gmail. ChatGPT responses are text-only, and need to be copied and pasted from the browser into a document. (Note: browser addons or plugins to capture responses are not discussed in this blog post. Any code you add to your browser this way should be researched thoroughly!)
Given that the content generated by Bard is not owned by the user, I will probably use ChatGPT for generating text and explaining concepts. (Of course, what ChatGPT generates should be verified!) I do prefer that responses are saved, and that different chats can be active.
It is possible that I might lean on Google Bard more for research questions, and will ask Bard for its sources. Undoubtedly the “Google it” button will be used in those efforts.
Of course, we can expect that Google Bard and other AI tools will continue to evolve at a rapid pace.
Based on the versions available at the time of this blog post being written, below is a table comparing features of OpenAI’s ChatGPT and Google Bard that I found notable.
Although Google Bard states that it removes personally identifiable information when using conversations to improve the model, DO NOT INCLUDE PERSONAL INFORMATION IN YOUR CHATS.
This week I spent some time working with Google’s challenger to OpenAI’s ChatGPT. Google Bard is a Language Model for Dialogue Applications (LaMDA), and I was working on the day that Bard began to bring images from Google Search into its results. Bard advertises that it helps you plan, solves complicated problems and supports your creative process. When it quotes content, it will cite where it found the material, or the computer code repository that was used.
In this article you will notice that I do include screenshots of answers, as I did for ChatGPT. That is because Google owns the generated content. If anyone wants to publish the content, they have to get permission from Google; at best Google and the user might share the rights to material. (In comparison, when you generate content in ChatGPT you own the rights to that content.)
You can select to save your Bard Activity, but even if that option is deselected, your activity is saved for up to 48 hours so that the feedback can be used. You can also select whether or not your activity is auto-deleted after 18 months. In my Bard Activity I could see the prompts that were given, but could not retrieve Bard’s responses, so remember to SAVE the responses. At the time of your session you can copy-and-paste them into a document or use the upload function described below.
The menu for Google Bard appears on the left hand side of the window.
At the bottom of each response were buttons to like, dislike, upload the response, or “Google it”
When you select to upload a response, you have options to upload it your Google Drive or draft an email in Gmail. The uploaded response will include text but NOT include the images you see in Bard.
I decided to ask some genealogically oriented questions, as I had done when testing ChatGPT.
“What are good resources for genealogy?” The answer to this prompt was a reasonable list of record databases, websites and societies.
“How can you help me with my genealogy?” This prompt was answered with ideas about genealogy research, finding resources, interpreting data and help create a family tree.
“How did someone travel from New York City to Newport, RI, in 1850?” Google Bard answered that the travel would have been by stage coach and steam ship, presenting me with images and data from the web along with its answer.
I asked what its sources were for this information, and it was listed sources. It also shared that it used its own knowledge to fill in the gaps.
When I asked how to find the source material, it provided links to places to buy a physical copy but did not provide a link to the source on Google Books. It did tell me that the book was available to view and download from Google Books. That resource was actually a very interesting discussion on travel to Newport between 1800 and 1850.
Since the user does not own the generated content, and the web is used to help answer prompts, this AI tool may be more useful to me as a research assistant.
Before I was a professor, I was a flight test engineer. My love of testing systems goes back to my early days working in a lab during college. My particular gift was always find a way to “break” hardware or software through use. My desire to investigate the use of ChatGPT in genealogy has definitely coincided with my enjoyment of testing. In this blog post, I take a look at what ChatGPT knows about GEDCOMs, how it builds one and how it can create a narrative when given an individual’s data formatted in a GEDCOM.
The technical jargon in this paragraph is available for those who want a slightly deeper understanding. In computer science, data can be grouped together in meaningful representation of things that live in the real world. A data structure is a way to group fields in a specific order for a program to input data, manipulate it, and output it. The way that genealogical data is formatted and shared is the GEnealogical Data COMmunication (GEDCOM) standard.
GEDCOM (Genealogical Data Communication) is a file format used to exchange genealogical data between different genealogy software programs. It is a standard format for saving family tree data, and it allows users to transfer their family tree data from one program to another.
GEDCOM files are saved with the extension “.ged” and are made up of text-based data that includes information about individuals, families, and events such as births, marriages, and deaths. The data is organized in a hierarchical format, with each record containing information about a single individual or event.
GEDCOM files can be used to create family trees, research family history, and share information with other genealogists. They are widely used by genealogy software programs and online genealogy databases. For example, you can export a GEDCOM from your family tree program or download a GEDCOM from Ancestry.com.
NOTE: DO NOT ENTER PRIVATE OR SENSITIVE DATA INTO ChatGPT. Your data is used for training, and is reviewed by OpenAI to verify that content complies with their policies and safety requirements. They may be used for training purposes.
I asked ChatGPT what it knew about GEDCOMs with prompts: What is a GEDCOM file? What is the GEDCOM standard? What are the fields in the GEDCOM standard?
ChatGPT answered reasonably well, except that it confidently stated the latest version of GEDCOM being used was 5.5.1. This is understandable because ChatGPT’s training ended in 2021. (As of the writing of this blog post, the current version is 7.0. For more information see the FamilySearch wiki entry for GEDCOM.)
Knowing that ChatGPT was using GEDCOM 5.5.1 was not a problem for these experiments.
Creating a GEDCOM
I would not choose to build a GEDCOM in this manner, but I could see how entering a narrative about ancestors into the prompt and let ChatGPT build the relationships from written language could be helpful. Beginning a family tree or adding a separate branch could be done by ChatGPT, then imported into a family tree program.
Investigating how effective ChatGPT was at creating a simple GEDCOM, I asked it to:
Create a GEDCOM file for James Charles McMahon, born 10 Oct 1920, father Joseph Francis McMahon, mother was Ella Small.
ChatGPT extracted the information from my request and filled in the fields. I only asked for a simple GEDCOM file, and had been very specific in what details to include. ChatGPT did fine with this request. You can see the button to copy the code so that I could store it in a file with a .ged extension that would be usable by a family tree program that conformed to the GEDCOM specification. In fact, it even warned me:
By the way, the clipboard next to the response lets a user copy the whole response so that a user can paste the response into the document of their choice. When clicked, the clipboard turns into a checkmark momentarily, then returns to being a clipboard. The thumbs up and thumbs down allow a user to provide additional feedback. If the feedback is thumbs down, another version of the reply is generated and a user has the opportunity to share whether the new one or previous response is better, or if they were the same. Giving feedback is always optional.
NOTE: This is a representation of an individual in a GEDCOM format and is not a file that can be directly imported into a family tree program. The header and footer information is not present, however, I could give ChatGPT that information and ask it to update the GEDCOM to include it.
I tried again with a new prompt that contained more details about the person’s life:
Create a GEDCOM file for James Charles McMahon, born 10 Oct 1920 in Brooklyn, Kings County, NY, father Joseph Francis McMahon, mother was Ella Small. James Charles McMahon died on 28 Nov 1987 in New York, New York, New York, US.
The response was filed the additional data correctly into the GEDCOM:
Using the GEDCOM as input to a family tree program
I asked for the file in a couple of different ways, but ChatGPT gave me only the section of the file for an individual. Rootsmagic had problems with importing this and creating a family tree, but after a little experimentation, I found that was because the was missing the header and trailer information. This was quickly remedied by editing the file.
It was interesting how the placeholder text for the birth and date information for the individual’s mother and father was inserted into the GEDCOM to be interpreted by the program. Of course, this could be fixed later in the conversation by asking for an updated GEDCOM with this information. As the chat went on, I also gave ChatGPT their marriage information and asked it to update the GEDCOM.
Creating a narrative from a GEDCOM
For my next experiment, I copied the second GEDCOM that ChatGPT had generated and fed it back into the prompt, asking:
Write a narrative for James Charles McMahon given his GEDCOM information:
0 @I1@ INDI
1 NAME James Charles /McMahon/
1 SEX M
[the rest of the file is not shown for brevity]
ChatGPT had learned details from our previous conversation, and inserted details about the individual learned from previous GEDCOMS. Starting the request in a new conversation brought its knowledge about the individual back to the nothing and the story included only the information from the prompt.
Of course, ChatGPT only uses what I told it. In reality, this individual was not an only child. Interestingly, after it writes that he grew up in a family of three, with himself and his parents, he was depicted as a beloved brother. This is due to large language models relying on their training to build the next part of their output.
Next, I checked if the format of the input mattered to ChatGPT, and made the GEDCOM data into one continuous stream, rather than distinct lines, in my prompt:
Write a narrative for James Charles McMahon given his GEDCOM information:
0 @I1@ INDI 1 NAME James Charles /McMahon/ 1 SEX M [the rest of the file is not shown for brevity]
ChatGPT did not need lines of the file to be formatted; it interpreted the data correctly then wrote a narrative. (This is also true when entering data from a table into the prompt.) Without information about the individual’s parents death, the model built the text that they survived him, and in the same sentence that they were deceased before his passing. ChatGPT can appear to loose its mind, so always proofread any output before using it.
Next, I carved out the lines for this individual from a GEDCOM that had been exported from a family tree program, complete with source citations embedded in the code. This text was used it as input to ChatGPT, and I asked it again to write a narrative from the GEDCOM. ChatGPT was successful in capturing the details it knew. It also created some generalizations like: “Throughout his life, James was a beloved member of his family and community.” It also added context without being prompted: “Though we don’t have much information about his specific experiences, we can imagine that he lived through many significant moments in history, including World War II and the civil rights movement.”
The tales that ChatGPT weaves from a user’s input can be a combination of technically accurate and fanciful. The facts that are input can be woven into a smoother and grammatically correct output. Any additional text that ChatGPT generates or additional contextual content it adds does need to be verified. ChatGPT is a generative language model that creates sentences without judgement, and those facts are presented as correct. (Always check the details that ChatGPT adds, as it may “hallucinate”!)
ChatGPT generates text with an optimistic tone. The tales do all seem to end on a positive note, reminding me of appending “and a good time was had by all” to a story.
As with any tool, how we used the output matters. ChatGPT has the flexibility to regenerate a response to our prompt, and we have the ability to edit the text as we see fit. This tool could be helpful to a genealogist trying to get started on that family history they have been planning to write. ChatGPT can help someone get around a writer’s block by providing a starting place. It can also proofread what you generate. All you have to do is ask.
It was instructive to see how the narrative text that was put into the prompt was translated into lines in the GEDCOM file. I enjoyed peaking under the hood of the implementation that is at the heart of family tree programs.
Let me know how you do, and send along any questions.
ChatGPT May 3 Version was used for these experiments. Expect ChatGPT to change over time as the technology matures.
Please check out other posts about ChatGPT and Artificial Intelligence:
You may have been wondering how ChatGPT can help with genealogical research. This is a first look at using ChatGPT for research about a specific ancestor. For simplicity our conversation focused on where to find information, rather than on more complicated topics. ChatGPT held its own in our conversation, and was a pleasant companion and offered answers based on its training.
NOTE: DO NOT ENTER PRIVATE OR SENSITIVE DATA INTO ChatGPT. Your data is used for training, and is reviewed by OpenAI to verify that content complies with their policies and safety requirements. They may be used for training purposes.
1. Ask ChatGPT general questions. Unless your ancestor is notable or famous, your main benefit will come from looking for general information about individuals with similar origins, living conditions or professions.
In my ongoing research into using ChatGPT for genealogical research, I decided to focus on one ancestor who has been a brick wall.
I started by asking if ChatGPT knew my ancestor. I did not expect an answer for an ancestor who was not a public figure, but I thought I would ask.
2. Forming questions/prompts is an important part of getting the most out of conversations with ChatGPT. Sometimes you need to rephrase or reformulate your approach to obtaining information.
I thought that ChatGPT might have more general information about immigrants from County Sligo, Ireland, so I asked a more general question::
ChatGPT answered with general information about Sligo immigrants, sharing their reasons for emigrating and where they tended to settle in the United States, and which popular professions they chose.
3. ChatGPT cannot footnote its answers. It can give sources that were used to build its knowledge base.
When I asked what sources ChatGPT what sources it used for the answer about Sligo. Since it is a trained artificial intelligence, and not a lookup service, this is like asking a person on the street to cite the sources for the statements they make in conversation.
In response, I reformulated my question:
ChatGPT offered five suggestions. This was more successful, until it was not. The suggestions were solid, but the details behind them were sometimes general and may not be up-to-date. (Remember, ChatGPT knows nothing of the world since 2021 and is NOT connected to the Internet.) The description it offered for civil registration records did not include the fact that many can be found online for free. The census records advice was factual about when censuses were conducted, but did not relate that only fragments exist for other than 1901 and 1911.
Civil registration records
Church records
Census records
Local history resources
DNA testing
4. Given a list of facts, ChatGPT can write a smooth narrative.
Next, I entered a text version of a timeline for Timothy Gilroy’s life. The text was copied then pasted into the prompt.
ChatGPT interpreted the data correctly, and fed back a narrative incorporating the facts. This was how I gave ChatGPT the data for my next questions.
5. ChatGPT can make good research suggestions. Treat ChatGPT’s research suggestions as hints. Be ready to investigate the leads it gives, keeping in mind that it may not know every aspect of every record set.
Remember that you are having a conversation with ChatGPT, and it remembers previous input in the same chat.
Next I asked: Can you suggest genealogical research ideas for Timothy Gilroy
ChatGPT pleasantly answered with a list of ideas. (Details of each item are omitted for brevity.)
Research his family in Sligo County, Ireland
Find records of his immigration
Locate records of his military service
Explore his occupation
Investigate his naturalization record
Look for church records
Conduct DNA testing
Since these were just “some” ideas, I asked: Do you have additional ideas?
ChatGPT was more than willing.
Explore the neighborhood where he lived
Investigate the history of Irish immigrants in Newport
Search for newspaper articles
Consult with local historical societies or genealogical societies
Utilize online genealogical resources
ChatGPT is ready and willing to help us research our ancestors. We have to be clear in our conversations, and be ready to ask questions from different perspectives. Overall, the ideas ChatGPT offered were sound. Of course, they were general and did not have all the potential constraints. ChatGPT stressed learning about context in many of the research questions, which was good. Of course, be sure to use its suggestions as just that, and not definitive facts.
The above conversation was with ChatGPT Mar 23 Version. Free Research Preview.
By now you have probably heard about OpenAI’s systen, ChatGPT. You can use the Preview Preview for free with an account. ChatGPT has a number of ways it can support the genealogical community, covered in Artificial Intelligence and Genealogy. It can also support your personal genealogical efforts, covered in other posts.
NOTE: DO NOT ENTER PRIVATE OR SENSITIVE DATA INTO ChatGPT. Your data is used for training, and is reviewed by OpenAI to verify that content complies with their policies and safety requirements. They may be used for training purposes.
Once you establish an account, using ChatGPT is as easy as typing in your questions or requests, which become the “prompts” to which ChatGPT generates responses. Underneath the hood, ChatGPT uses prompt engineering as part of its natural language processing capabilities to get meaningful responses from its models. Knowledge databases, texts, and other sources as well as an understanding of language has been used to train its neural network. When it has not been trained about a specific topic, it uses relevant information from external sources. ChatGPT answered a few questions about this for me. ChatGPT told me it did not search the web as humans would. In fact, ChatGPT is not connected to the Internet, and it has limited knowledge of world events after 2021. In response to another question, ChatGPT answered that it did not need question marks for it to understand that I asked a question, but that using them might clarify the input.
You can use the research preview of ChatGPT for free. You own the output that is created. The output from a paid or free plan can be reprinted, sold and merchandised.
To get a free research account https://chat.openai.com/and select “Sign up” and follow the steps.
To sign up for an account, you have to provide your email address and a phone number. The email address and phone number do have to be validated before your account is activated.
The “Send a message…” box at the bottom is where to type a question or issue a request.
At the end of the generated response, you can continue the conversation by asking another question. You also have the option to select “Regenerate response” to make ChatGPT process the request again and generate another response.
NOTE: If you choose to REGENERATE RESPONSE, the original one will be replaced. So, if you are looking to combine or compare responses, be sure to copy the original response.
Your conversations will appear on the left side of the screen in a laptop or desktop browser. You have the option to edit the automatically assigned label for the chat, or delete it. There is also an option to begin a “New chat.” NOTE: Conversations with the Free Research Preview are reviewed to improve systems and to verify that content complies with their policies and safety requirements. They may be used for training purposes. You can request to delete your conversations from a link in the FAQ.
Here is an example where I started out with a simple question in my message prompt: What is a GEDCOM file?
ChatGPT answered this prompt. While it was answering, there was an option to “Stop generating” the response. Note the “Regeneration response” button at the bottom of the reply.
In the image above, you can see the thumbs up and down buttons so that you can provide feedback by about the answers.
The same prompts generated different responses, as evidenced by the regenerated responses. To see if the responses might be presented in a preplanned sequence, I asked a friend to enter the same prompt (different than the example given). The response she received certainly had similar elements, but the responses were definitely not the same. The responses were more different than rearranged words; the concepts were expressed in a different manner.
The conversations you have with ChatGPT can be saved through browser addons, but I found it far simpler to copy-and-paste into Word or Wordpad documents (for now).
As for how long my input prompt could be, I asked ChatGPT directly about that. The answer is 2048 tokens, which can be interpreted as characters. ChatGPT needs you to know that a spaces and punctuation marks count.
This technology really is impressive. I began with giving specific prompts but before too long I found myself falling into a pattern like conversation with the ChatAPT. It seemed very natural. I could also ask for clarification about a previous answer, or change the intent of my question. I could lead the conversation in different directions based on the responses. According to the ChatGPT FAQ, https://help.openai.com/en/articles/6783457-chatgpt-general-faq
ChatGPT Mar 14 Version of the Free Research Preview was used for examples in this tutorial. Future releases may have slightly different interfaces and options.
