This class provides an in-depth description about how to extend your family history research using descendancy lines. The example is based on my experience researching a Jewish ancestral line that extends from the United States through Australia to England and then on to the Netherlands.
This is one of more than 860 videos on the BYU Family History Library YouTube Channel. As I have mentioned in the past, I am finding videos to be a better way of teaching and reaching a large audience than blog posts. During the past month, I have posted about twelve videos and I have many more scheduled. You can see the future videos on the BYU Family History Library website or https://fh.lib.byu.edu/.
The Turing test is a test proposed by the British mathematician and computer scientist Alan Turing in 1950. It is designed to evaluate a machine's ability to exhibit intelligent behavior that is indistinguishable from that of a human. The test involves a human judge engaging in a natural language conversation with a machine and a human, without knowing which is which. If the judge cannot reliably differentiate between the machine and the human based on their responses, the machine is said to have passed the Turing test. ChatGPT
If you think about this description of the Turing Test, you might immediately detect the definition's fatal flaws. The flaws are with the human participants. What if the two human participants do not speak the same language or have approximately the same level of intellectual ability? This problem has been addressed academically by discussions involving the question of when a machine becomes intelligent. There is no question that some machines can do things faster and better than any human. Here are some links to articles discussing different aspects of the intelligence question.
The question of when a machine becomes intelligent is a topic of ongoing debate and discussion. Intelligence itself is a complex and multifaceted concept, and there are different ways to define and measure it.
In the field of artificial intelligence (AI), machines are considered intelligent when they can perform tasks that typically require human intelligence. This can include capabilities such as learning from data, reasoning, problem-solving, recognizing patterns, and making decisions.
Traditionally, AI has been divided into two main categories: narrow or weak AI, and general or strong AI. Narrow AI refers to systems that are designed to perform specific tasks or functions with a high degree of competence, such as image recognition or natural language processing. General AI, on the other hand, refers to systems that possess the ability to understand, learn, and apply knowledge across a wide range of tasks similar to human intelligence.
Currently, most AI systems in use are considered narrow AI, where they excel at specific tasks but lack the broader cognitive abilities associated with human intelligence. However, as technology advances, there is ongoing research and development aimed at achieving general AI.
The exact point at which a machine can be considered truly intelligent is subjective and may vary depending on the criteria and perspective used. Some argue that intelligence requires consciousness and self-awareness, while others focus on the ability to exhibit human-like cognitive functions regardless of consciousness.
It's important to note that there is no consensus on a definitive threshold for machine intelligence, and the field of AI continues to evolve with ongoing research, advancements, and new discoveries.
It is interesting that ChatGPT did not refer to the Turing Test at all. Can I tell that the text above was written by a computer program? How is using ChatGPT different that looking up articles, like I did above. Is the fact that the computer program in looking at the same data was able to give cogent response make any difference? Tellingly, the computer program did not quote any of the abundant source articles on the subject. By the way, I consider the ChatGPT response to be overly wordy and superficial.
But what about the Turing Test? My answer would be it is no longer relevant. Another note, there are now computer programs that can tell if what is written above was written by ChatGPT or was the original work of a person. See the following:
Somewhere between appearing in Isaac Asimov's book, I, Robot, in 1950 and the latest StarWars movie or series, artificial intelligence became a threat to civilization as we know it for newscasters and pundits around the world. In a class at a local FamilySearch Center recently, I referred to some of the current advances in artificial intelligence and one of the class participants asked if there was going to be anything left for genealogists to do. I didn't have either a complete or even accurate answer to that question. But as is always the case when I don't have an immediate answer to a question, I could not help but continue to think about the consequences of the present and future advances of artificial intelligence and the effect it may have on genealogical research.
I have recently addressed some of the issues of genealogy and AI (I am tired of typing out the complete term) recently in blog posts. Here are the links.
Yes, AI is a threat to civilization as we know it. In the same way that fire, gunpowder, atomic energy, and a vast number of other developments have affected civilization. Forty-one years ago, or so, when I started my genealogical research into my own family, I lived in an almost completely paper-based society. The only technology I was using was microfilm invented back 1839 by John Dancer. See The History Of Microfilm | Learn The Past , Present, And Future. I remember trying to use the United States Federal Census on microfilm and immediately becoming discouraged because it was hard to read, and I did not yet know about Soundex. Here is a short explanation of Soundex from a Google search.
The Soundex is a phonetic algorithm for indexing names by sound, as pronounced in English. It was developed by Robert C. Russell and Margaret King Odell and patented in 1918 and 1922. The National Archives began indexing US Census Records in 1880.
The Soundex is a coded surname index (using the first letter of the last name and three digits) based on the way a name sounds rather than the way it's spelled. Surnames that sound the same but are spelled differently - such as Smith and Smyth - have the same code and are filed together.
The Soundex indexes include heads of households and persons of different surnames in each household.
Back in the 1950s, AI was just beginning to capture the interest of those outside of the academic community. Here is a quote about the beginnings of AI.
In the first half of the 20th century, science fiction familiarized the world with the concept of artificially intelligent robots. It began with the “heartless” Tin man from the Wizard of Oz and continued with the humanoid robot that impersonated Maria in Metropolis. By the 1950s, we had a generation of scientists, mathematicians, and philosophers with the concept of artificial intelligence (or AI) culturally assimilated in their minds. One such person was Alan Turing, a young British polymath who explored the mathematical possibility of artificial intelligence. Turing suggested that humans use available information as well as reason in order to solve problems and make decisions, so why can’t machines do the same thing? This was the logical framework of his 1950 paper, Computing Machinery and Intelligence in which he discussed how to build intelligent machines and how to test their intelligence. See
Computing machines were (and still are) viewed as a threat to jobs, culture, morality, and the rest of the world as we know it, long before the internet and Google. The first part of my life up until about 1972 was spent in this pre-computer age and when I think about what would have been different if I had access to computers during high school still disturbs me. Here is a timeline of AI from ChatGPT (which is currently integrated into my Chrome browser).
1943-1955:
1943: Warren McCulloch and Walter Pitts introduce the concept of artificial neural networks.
1950: Alan Turing proposes the "Turing Test" as a measure of machine intelligence.
1951: Christopher Strachey develops the first chess program for the Ferranti Mark I computer.
1956-1979:
1956: John McCarthy organizes the Dartmouth Conference, widely considered the birth of AI as a field.
1958: Frank Rosenblatt invents the Perceptron, a fundamental model for machine learning.
1966: The concept of "ELIZA," a natural language processing program, is introduced by Joseph Weizenbaum.
1969: Shakey, an autonomous robot, is developed at Stanford Research Institute, showcasing the potential of AI in robotics.
1980-1999:
1980: The first commercial expert system, MYCIN, is developed to diagnose blood infections.
1985: Terry Winograd develops SHRDLU, an early natural language understanding program.
1997: IBM's Deep Blue defeats world chess champion Garry Kasparov, marking a milestone in AI's ability to defeat human experts.
1997: Rodney Brooks introduces the concept of behavior-based robotics with the development of the robot "Cog."
2000-2010:
2002: The DARPA Grand Challenge is launched, a competition for autonomous vehicles.
2005: Stanford University introduces the Stanford Autonomous Helicopter project, demonstrating advanced machine learning techniques.
2006: Geoffrey Hinton introduces deep learning algorithms that revolutionize speech and image recognition.
2011: IBM's Watson defeats human champions on the quiz show "Jeopardy!"
2011-2021:
2015: OpenAI, an AI research organization, is founded by Elon Musk, Sam Altman, and others.
2016: DeepMind's AlphaGo defeats world Go champion Lee Sedol, demonstrating AI's progress in complex strategy games.
2017: AlphaGo Zero is developed, surpassing its predecessor without any human data or guidance.
2020: GPT-3 (Generative Pre-trained Transformer 3) is released by OpenAI, showcasing advanced natural language processing capabilities.
2021: Researchers develop models capable of generating highly realistic deepfake images and videos, raising concerns about misinformation.
2022-Present:
Ongoing advancements in AI research and applications across various fields, including healthcare, finance, transportation, and more.
Continued efforts to address ethical considerations, privacy concerns, and the responsible deployment of AI technologies.
Ongoing development of advanced AI models, reinforcement learning techniques, and exploration of AI's potential in solving complex problems.
Please note that this timeline provides a broad overview of key milestones in AI history and is not exhaustive. AI research and advancements continue at a rapid pace, and there may be significant developments beyond my knowledge cutoff in September 2021.
You are welcome to fact check any of the entries. Some of the dates are approximate for ongoing events.
Genealogy is an information pursuit, and it is bound by its very nature to be affected by AI. The recent developments in AI make this inevitable. Stay tuned for further comments.
If you have noticed that the number of blog posts has dropped, the main reason is that the time I used to spend blogging has now become the time I spend doing videos, helping with live classes, consultations, and teaching missionaries and patrons at the BYU Family History Library. Each video takes about eight hours of production time. Most of the videos are available on the BYU Family History Library YouTube channel, although some of them are posted on The Family History Guide website. The total number of my videos on YouTube and the rest of the internet now is something over 400. I have a list of future topics for release that extends well into 2024.
Just for some reference, according to Google's current count, I have posted 6,239 blog posts on Genealogy's Star blog since I began many years ago.
Lately, I have been exploring the possibility of using artificial intelligence to accelerate both my blog posting and my video production. I will be reviewing some of the things I have found as I learn about all the new developments. I am expecting that by using the developments in AI, I will be able to increase the number of videos I do weekly, significantly. If you want to learn about artificial intelligence, here is a suggested list of ways to learn about the subject generated in about 5 seconds from ChatGPT and Microsoft Bing.
Learning about artificial intelligence (AI) is an exciting and rapidly evolving field. Here's a step-by-step guide to help you get started:
Familiarize Yourself with AI Concepts:
Begin by understanding the fundamental concepts of AI, such as machine learning, neural networks, and data analysis. Books like "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig provide a solid introduction.
Online Courses and Tutorials:
Enroll in online courses that cover AI topics. Platforms like Coursera, Udacity, and edX offer courses on machine learning and AI. Popular courses include Andrew Ng's "Machine Learning" and "Deep Learning Specialization."
Explore online tutorials and resources, such as TensorFlow's official website, which provides tutorials for building AI models.
Python Programming:
Learn Python, as it is widely used in AI development. Python provides libraries and frameworks like TensorFlow, Keras, and scikit-learn that make AI implementation easier.
Start with introductory courses or tutorials for Python, and gradually progress to libraries and frameworks specifically designed for AI.
Practical Projects:
Gain hands-on experience by working on AI projects. Start with small projects like image classification or sentiment analysis using existing datasets. Websites like Kaggle provide datasets and competitions to enhance your skills.
Join AI Communities:
Engage with AI communities to stay updated and learn from experts. Participate in forums like Reddit's /r/MachineLearning and AI-related discussion groups on LinkedIn. Attend AI conferences and meetups if possible.
Read Research Papers and Blogs:
Dive into research papers to gain insights into cutting-edge AI techniques. Platforms like arXiv and Google Scholar host numerous papers.
Follow AI-focused blogs and newsletters to stay updated with the latest advancements. Some popular ones include "Towards Data Science," "Medium AI," and "OpenAI Blog."
Online Video Content:
Explore YouTube channels dedicated to AI and machine learning. Channels like "Two Minute Papers," "Sentdex," and "Lex Fridman" provide informative videos and interviews with AI experts.
Advanced Topics:
Once you have a solid foundation, you can explore advanced topics like natural language processing, computer vision, reinforcement learning, and generative models.
Remember, AI is a vast field, and continuous learning is essential. Stay curious, practice coding, and work on real-world problems to strengthen your AI skills.
Granted, some of this stuff is more technical than even I want to get into, but what is being generated and currently used to advance genealogical research and my video production is significant.
I haven't closely fact-checked the above quote, but you can assume that anything I use for my own writing or video production will be well fact-checked.
Several years ago, my wife and I began working at the Brigham Young University (BYU) Family History Library. We also began working with The Family History Guide Website.
We recognized that The Family History Guide was a valuable resource for teaching the missionary volunteers in the library. Now, for at least the last seven or eight years, the BYU Family History Library has been using The Family History Guide to teach the missionary staff that serve in the library as Church Service Missionaries for The Church of Jesus Christ of Latter-day Saints. Eventually, The Family History Guide was accepted for teaching the Church Service Missionaries serving in the Utah Salt Lake City Headquarters Mission. Now, the lessons used to teach the missionaries about the FamilySearch.org Family Tree are available on the FamilySearch.org website for the benefit of any user.
You can navigate to the Family Tree Basics page with the links to The Family History Guide by first, clicking on the question mark icon in the upper right-hand corner of the homepage.
You then click on the link for "Help and Learning."
When you arrive at the Help and Learning page and scroll down to the Learning Center link that says, "Build Skills, Make Progress."
You are now in the Learning Center and can then click on the link for Family Tree Basics.
Another click will take you to list of lessons shown above at the beginning of this post.
To get there directly, you can click on this link.
Each lesson begins with a Learning Road Map and then the lessons are from The Family History Guide.
All of us at The Family History Guide Association are grateful for this opportunity to reach a wider audience for learning about the FamilySearch.org Family Tree. If you need help or have any questions, please feel free to contact me or my wife at the BYU Family History Library.
You can also get help from the BYU Family History Library by clicking on the link to the Virtual Family History Help Desk. Here is an explanation about how that works.
This is James Tanner. My wife, Ann, and I can meet with you on the BYU Family History Library Virtual Help Desk during the time the Help Desk is available. Here is the link to the BYU Family History Library, https://fh.lib.byu.edu/ I have attached a screenshot of the web page for reference. When you click on the link button, you will see the second page. https://fh.lib.byu.edu/live-virtual-missionary-help/ See also the screenshot attached. When you click on this link you will be connected to a Zoom meeting online at the library. You can ask for help from the missionaries, or we can schedule to meet. If we set a time to meet, I will be there waiting for you online and we will go to a breakout room and talk and share screens.
One of the most innovative and useful programs that have been developed in the past few years, GoldieMay.com is now included in the FamilySearch Portal and is therefore free to use in all FamilySearch Centers.
If you need a quick review about the program, here is a video from YouTube.com
Posts
