Disclaimer: Due to the technology limitations of this blog post, I was unable to create a chart to compare the answers to the questions and my references are not using true APA formatting, as they lack hanging indents.
1. First and in your own words: Who were these people, and how did/does each contribute to the development of artificial intelligence? How did/does each think “intelligence” could be identified? (~50 words each). Next, using the new AI ChatGPT. ask it the same question, and you can edit to get it down to 50 words. Create a chart to show your work and ChatGBT side by side. Do the same with questions 2-4 (and do make sure in YOUR answers you reference the readings!).
Alan Matheson Turing (1912-1954)
My response
Alan Turning, a British mathematician named the father of computer science and AI, broke the Nazi’s ciphers during World War II to help the Allies defeat the Axis (Alan Turing, 2024). Turing viewed the concept of intelligence as emotional (Turing test, 2024). The Turing proof concluded that some mathematical questions cannot be answered (Turing’s proof, 2024).
ChatGPT – Prompt: “Who was Alan Turing and how did he view intelligence in 50 words or less”
Alan Turing (1912–1954) was a British mathematician and computer scientist. He viewed intelligence as a universal computation process, proposing the Turing Test to assess machine intelligence. Turing’s work in breaking German Enigma codes during WWII and his contributions to theoretical computer science laid the foundation for modern computing and AI.
John McCarthy (1927-2011)
My response
John McCarthy, a founding father of AI, was an American computer scientist and Stanford professor. He formally introduced the term “artificial intelligence”, created AI as a field, and developed the programming language Lisp (John McCarthy, 2023). He believed there is no difference between human and machine tasks (Crawford, 2021).
ChatGPT – Prompt: “Who was John McCarthy and how did he view intelligence in 50 words or less”
John McCarthy (1927–2011) was an American computer scientist and AI pioneer. He coined the term “artificial intelligence” and viewed intelligence as computational problem-solving. McCarthy contributed to early AI systems and the development of the programming language LISP. His work focused on creating machines capable of general problem-solving and learning.
Herb Simon (1916-2001)
My response:
Herb Simon was an American political scientist and one of the founding fathers of AI. He was famous for his views on decision-making which he believed was a crucial part of intelligence (UBS, n.d.). Simon proposed that machines could have emotional cognition which was mostly ignored then eventually became influential (Herbert Simon, 2024).
ChatGPT – Prompt: “Who was Herb Simon and how did he view intelligence in 50 words or less”
Herbert A. Simon (1916–2001) was an American economist, cognitive psychologist, and Nobel laureate. He viewed intelligence as bounded rationality, emphasizing that human decision-making is constrained by limited information and cognitive resources. Simon’s work laid the groundwork for behavioral economics and influenced the study of artificial intelligence and cognitive science.
Marvin Minsky (1927-2016)
My response:
Marvin Minsky was an American cognitive and computer scientist who believed machines can think and intelligence in humans and computers is equal (Chollet, 2019; Crawford, 2021). He co-developed the Logo “turtle” and the Society of Mind theory with Seymour Papert that explains how intelligence is task-focused and is a product of interacting components (Chollet, 2019; Marvin Minsky, 2024).
ChatGPT – Prompt: “Who was Marvin Minsky and how did he view intelligence in 50 words or less”
Marvin Minsky (1927–2016), a pioneering AI researcher, viewed intelligence as a collection of interconnected processes, emphasizing the role of perception, learning, and problem-solving. Co-founder of MIT’s AI Lab, Minsky explored the idea of “frames” and “agents” in AI, contributing to the understanding of complex cognitive functions and machine learning.
Timnit Gebru (1982)
My response:
Timnit Gebru is an Ethiopian-born computer scientist who researches AI, biases in AI, and data mining. She advocates for ethical uses of AI and diversity in technology. Gebru was fired from Google after criticising their biased AI work. Gebru views intelligence as diverse and should benefit all humans (Al Jazeera English, 2022).
ChatGPT – Prompt: “Who is Timnit Gebru and how does she view intelligence in 50 words or less”
Timnit Gebru is an Ethiopian-American computer scientist known for her work in artificial intelligence ethics and bias. She co-authored influential research on bias in facial recognition technology. Gebru advocates for ethical AI development and has been an influential voice in addressing issues of fairness, accountability, and transparency in AI systems.
2. How do “machine (programming) languages” differ from human (natural) ones? (~100 words).
My response:
Machine and human languages are both systems of communication. Human languages are ever-evolving and help us interact with others. Humans are generally better than computers at discerning meaning by using context and inferences (Jones, 2019, p. 27). Natural languages, like English, evolve over time and can be spoken or written, and even include gestures (Language, 2024). Machine languages differ from human languages because they are special languages built on algorithms and are executable (Galloway, 2009, as cited in Jones, 2019). Machine languages are a set of sequential instructions that tell the computer’s CPU what to do (Machine code, 2023). Machine languages are built by humans and they only understand what humans tell them to understand.
ChatGPT: How do “machine (programming) languages” differ from human (natural) ones? (~100 words).
Machine (programming) languages and human (natural) languages differ fundamentally in their purpose and structure. Machine languages, such as Python or C++, are designed for computers to execute specific instructions, focusing on precision and efficiency. They use syntax and logic tailored for programming tasks. In contrast, human languages, like English or Spanish, serve communication between people and encompass diverse nuances, emotions, and abstract concepts. Human languages are expressive and context-dependent, emphasizing the richness of communication, while machine languages prioritize clarity and exactness for computers to interpret and execute instructions accurately (OpenAI, 2023).
3. How does “machine (artificial) intelligence” differ from the human version? (~100 words).
My response:
Many attempts have been made to define intelligence yet it has been difficult to develop one definitive definition (Chollet, 2019). Chollet (2019) discusses how intelligence can be perceived as task-specific skills or a general learning ability, then uses Algorithmic Information Theory to propose a new definition of intelligence. Human intelligence uses pragmatics to make sense of situations (Jones, 2020). Machine intelligence follows the instructions that humans have programmed it with the hopes of mimicking human intelligence and can recognize patterns that humans do not have the capacity to process, as we saw in the large amounts of data analyzed with the Cambridge Analytica example of “pragmatics on steroids” (Jones, 2020).
ChatGPT – Prompt: How does “machine (artificial) intelligence” differ from the human version? (~100 words).
Machine (artificial) intelligence differs from human intelligence in several key aspects. While artificial intelligence (AI) excels at specific tasks through programmed algorithms and data analysis, it lacks the depth and breadth of human intelligence. Human intelligence encompasses emotional understanding, creativity, social awareness, and complex problem-solving, whereas AI is task-oriented and lacks genuine consciousness. Human intelligence is dynamic, adaptable, and driven by consciousness, self-awareness, and subjective experiences, which remain elusive in artificial intelligence. While AI can perform specific tasks efficiently, it falls short of replicating the holistic and multifaceted nature of human intelligence (OpenAI, 2023).
4. How does “machine learning” differ from human learning? (~100 words)
My response:
As we learned in ETEC 512, there is no best or correct theory that can account for all aspects of human learning – human learning is complex and is based on many factors such as biology, prior experiences, and sensory input. Human learning uses intelligence that can be used to program machine learning through using data and models. Machine learning is a branch of AI where machines can learn to process data without explicit instructions using algorithms and they can “learn” to generalize in novel situations as they are exposed to more data over time (Machine learning, 2024).
ChatGPT – Prompt: How does “machine learning” differ from human learning? (~100 words)
Machine learning and human learning differ in their processes and origins. Machine learning involves algorithms and computational models that enable computers to improve their performance on a task through experience or data. It relies on statistical patterns and mathematical optimization. In contrast, human learning is a complex, multifaceted process that involves cognitive, emotional, and sensory aspects. Humans can generalize knowledge, apply intuition, and learn from a wide range of experiences, adapting to new situations with flexibility and creativity. While both involve learning from data, the mechanisms and scope of machine learning and human learning are distinct. (OpenAI, 2023)
5. And for your LAST challenge, a version of the Turing Test: how do YOUR answers to these questions differ from what a machine could generate? make sure you reference the specific differences between your answers and ChatGPT’s. (~200 words)
There are many differences between my answers to the above questions and the answers generated by ChatGPT.
First, ChatGPT is fast. ChatGPT took seconds to process in the specified number of words, whereas my answers took many hours of reading, synthesizing, and staying within the word counts.
Second, ChatGPT did not provide references to its sources of information, whereas my answers have citations. I pulled together references using APA formatting from the course readings whereas ChatGPT did not use the specified readings, nor do I have a way of checking for its plagiarism or find the primary source of information to refer to.
Third, ChatGPT does not understand the nuances within the context of this course, the relevance to the MET program, or to the fields of Educational Technology.
Lastly, ChatGPT does not factor in the rubric as provided by our ETEC 511 professor which is a personally relevant consideration in this assignment.
The end result is that these answers are not that different from each other but I do hope my answers come across as more “human” as they are based on my personal reflections, experiences, and the nuanced expectations of this course.
References
Al Jazeera English. (2022, August 5). Timnit Gebru: Is AI racist and antidemocratic? | Talk to Al Jazeera [Video]. YouTube. https://www.youtube.com/watch?v=vUJVzIdRSnQ
Alan Turing. (2024, January 19). In Wikipedia. https://en.wikipedia.org/wiki/Alan_Turing
Biography. (2020, July 22). Alan Turing. https://www.biography.com/scientists/alan-turing
OpenAI. (2023). ChatGPT (Mar 14 version) [Large language model]. https://chat.openai.com/chat
Chollet, F. (2019, November 5). On the measure of intelligence.
Crawford, K. (2021). Atlas of AI. Yale University Press. (Introduction: pp. 1-21)
Herbert A. Simon. (2024, January 23). In Wikipedia. https://en.wikipedia.org/wiki/Herbert_A._Simon
John McCarthy (computer scientist). (2023, December 5). In Wikipedia. https://en.wikipedia.org/wiki/John_McCarthy_(computer_scientist)
Jones, R. H. (2020). The rise of the Pragmatic Web: Implications for rethinking meaning and interaction. In C. Tagg & M. Evans (Eds.), Message and medium: English language practices across old and new media (pp. 17-37). De Gruyter Mouton.
Language. (2024, January 28). In Wikipedia. https://en.wikipedia.org/wiki/Language
Machine code. (2023, December 10). In Wikipedia. https://en.wikipedia.org/wiki/Machine_code
Machine learning. (2024, January 29). In Wikipedia. https://en.wikipedia.org/wiki/Machine_learning
Marvin Minsky. (2024, January 4). In Wikipedia. https://en.wikipedia.org/wiki/Marvin_Minsky
McCarthy, J. (2007, November 12). What is Artificial Intelligence? https://www-formal.stanford.edu/jmc/whatisai/node1.html
Timnit Gebru. (2024, January 16). In Wikipedia. https://en.wikipedia.org/wiki/Timnit_Gebru
Turing’s proof. (2024, January 8). In Wikipedia. https://en.wikipedia.org/wiki/Turing%27s_proof
Turing test. (2024, January 7). In Wikipedia. https://en.wikipedia.org/wiki/Turing_test
UBS. (n.d). Meet the Nobel Laureates in economics: Do we understand human behaviour? https://www.ubs.com/microsites/nobel-perspectives/en/laureates/herbert-simon.html