IP 2 - Artificial Intelligence Overview
IP 2 hopes to capture a brief history and overview of artificial intelligence as a computer science while attempting to briefly distinguish the concepts of intelligence and learning between humans and machines. This IP also highlights a Turing Test of it’s own as it includes a comparison and analysis of my responses to those of ChatGPT when given the same prompts. Enjoy.
-
Alan Turing was an influential and foundational researcher of computing and artificial intelligence. In Turing’s widely-cited work, he finds that defining intelligence is futile and that the ability to think might be conceptualized as a perception based on our experienced interactions; can we distinguish responses between human and a machine.
ChatGPT: “Alan Turing was a British mathematician and logician who laid the theoretical groundwork for artificial intelligence. He proposed the concept of a "universal machine" (the Turing machine) and the Turing Test, a benchmark for machine intelligence. He believed intelligence could be identified by a machine's ability to imitate human conversation indistinguishably.” -
John McCarthy was a Stanford professor with a keen interest in programming who perhaps is best known for coining the term “artificial intelligence” in 1955. He is also the inventor of the programming language LISP, Stanford’s AI Lab, and worked closely on the concept of time-sharing which is more widely recognized as “multiprocessing” in our computers today. He believes AI is the science and engineering of thinking machines, but defining machine intelligence is still dependent on our understanding of human intelligence.
ChatGPT: “John McCarthy, an American computer scientist, coined the term “artificial intelligence” and developed the Lisp programming language. He emphasized logic-based reasoning and symbolic processing. McCarthy believed intelligence involved the ability to use language, form abstractions, and solve problems, and that machines could be built to perform these functions autonomously.”
-
Herb Simon was an American economist and mathematician who placed a high value on data-informed decision-making. His creation of the “Logic Theorist” is accepted as one of the first artificial intelligence programs as it imitated human problem-solving abilities. Simon’s identification of intelligence could be interpreted as the ability to recognize patterns from information that is processed and stored.
ChatGPT: “Herbert Simon was a pioneer in AI and cognitive science who focused on problem-solving and decision-making. He co-developed the Logic Theorist, one of the first AI programs. Simon argued that intelligence could be identified through bounded rationality—how well an agent makes decisions with limited information and resources.”
-
Marvin Minsky was the co-founder of MIT’s AI lab along with John McCarthy. He believed artificial intelligence was any intelligence used for a task that would be needed by a human for the same task.
ChatGPT: “Marvin Minsky was a cognitive scientist and co-founder of MIT’s AI Lab. He viewed the mind as a collection of interacting agents (The Society of Mind theory). Minsky believed intelligence emerged from the interaction of simpler non-intelligent parts and could be replicated through computational models of these interactions.”
-
Dr. Timnit Gebru is the director of the Distributed AI Researchcentre. She has worked throughout her career to ensure accountability within AI systems and large language models. In a 2025 interview she states that “artificial intelligence”is hard to define because it is not static. She believes AI might be defined by whatever the stakeholder claims it to be based on the technology being used/proposed.
ChatGPT: “Dr. Timnit Gebru is a computer scientist and ethical AI researcher known for her work on algorithmic bias and AI’s societal impact. She critiques how intelligence is defined and measured in AI, emphasizing that ethical concerns and cultural contexts must inform definitions. She questions traditional metrics and calls for accountability in AI systems.”
prompts
How do “machine (programming) languages” differ from human (natural) ones? (~100 words).
My response
Human language and machine languages are both communication tools that are highly structured. My research and experience leads me to the belief that the main difference is the way human language can be used. When writing, humans “play” with the syntax and semantics of words to subvert set rules and evolve language and create new meanings. Machine languages have traditionally been built in the binary - the instructions either work or don’t work. Due to zero error tolerance, machine languages cannot evolve in the way human languages can. It is interesting to note the evolution of neural networks dating back to the 1950s and how current research looks to create machine languages with more abstract capabilities.
Learning as defined by the acquisition of new knowledge, skills, or understanding, does not differ from human to machine. However, the process of learning does. As of now, machines are dependent on humans to train them using data-sets. Humans, on the other hand, learn through various ways, both consciously and unconsciously as they interact with their environments and receive feedback from them. In this way, although a machine may learn faster than a human, it is limited to the availability of the data and is not influenced by experience, context, and ultimately a conscience.
CHATGPT RESPONSE
“Machine (programming) languages and human (natural) languages differ in structure, purpose, and ambiguity. Programming languages are formal, rule-based systems designed to communicate instructions to computers. They require precise syntax and produce consistent outputs; even a small error can cause a program to fail. In contrast, natural languages like English are flexible, context-dependent, and often ambiguous, shaped by culture and human interaction. Humans infer meaning from tone, gesture, and shared experience, while machines rely on exact code. Programming languages prioritize clarity and logic, whereas natural languages evolve organically and prioritize expression, nuance, and adaptability in human communication.”
How does “machine (artificial) intelligence” differ from the human version? (~100 words)
How does “machine learning” differ from human learning? (~100 words)
Defining intelligence for humans is difficult, which complicates differentiating it from artificial intelligence. A cognitive approach to human intelligence might define intelligence as our mental representations and ability to process and communicate based on those representations. Chollet (2019) offers a deeper consideration of human intelligence that suggests it is the efficiency of learning based on prior knowledge, our experiences, and the ability to generalize. Artificial intelligence seeks to mimic human cognitive abilities, relying on data that comes from humans. In this way, it cannot reproduce positive intellectual elements of ethics, creativity or perception. However, on the other hand, the application of machine intelligence is less impacted by factors like fatigue and stress which affect human accuracy.
“Machine (artificial) intelligence differs from human intelligence in origin, flexibility, and consciousness. AI is designed by humans to perform specific tasks like recognizing patterns, making predictions, or generating language based on data. It lacks self-awareness, emotions, and true understanding. Human intelligence, by contrast, is biological, adaptive, and shaped by experience, emotion, social context, and creativity. While AI can outperform humans in narrow domains (e.g., calculations, game strategies), it struggles with generalization, ethical reasoning, and common sense. Human intelligence is holistic, involving abstract thought, empathy, and intentionality—qualities that AI mimics superficially but does not genuinely possess.”
“Machine learning differs from human learning in process, adaptability, and understanding. Machine learning involves algorithms detecting patterns in large datasets to make predictions or decisions without being explicitly programmed. It relies on statistical models, requires vast amounts of data, and lacks true comprehension. Human learning, however, is experiential, contextual, and influenced by emotions, intuition, and social interaction. Humans can learn from few examples, reason abstractly, and apply knowledge creatively across situations. While machine learning excels in data-driven tasks, it lacks the consciousness, motivation, and meaning-making that define human learning. Ultimately, machines process information; humans derive understanding and purpose from it.”
Comparing my responses to ChatGPT
In my opinion, it is relatively obvious when a response is directly copied from a large language model like ChatGPT. To compare, let’s look at similarities between my responses and the generative responses. When looking at the biography entries, we seem to both mention key places of employment and/or achievements. In the longer form response questions, we have some similar ideas. We both reference “syntax” in our answer about language and also do our best to highlight the nuanced ways humans use language to differentiate them from machines. In the second prompt about intelligence, we both reference ethics and creativity as key differences. However, ChatGPT’s writing seems overall more concise and polished than my responses. Since I knew I would be compared, I tried to take extra steps to differentiate myself from what I thought the large language model would do. I’m not sure I would define this as truly transformative, but I did two specific things to create this difference. First, I tried to weave my opinion and understanding of the sources into my responses with a sort-of professional informality (e.g., “Defining intelligence for humans is difficult, which complicates differentiating it from artificial intelligence”) that gave my writing a personality. Second, I tried using hyperlinks to creatively craft and source my responses (e.g., “It is interesting to note the evolution of neural networks dating back to the 1950s and how current research looks to create machine languages with more abstract capabilities.”) which ChatGPT does not explicitly do. Overall, the high quality of summative writing by ChatGPT and the slight personality of my writing are key differences in this exploration of artificial and human intelligence.
References
BBC News. (2016, January 26). AI pioneer Marvin Minsky dies aged 88. https://www.bbc.com/news/technology-35411661
Biography. (2020, July 22). Alan Turing. https://www.biography.com/scientists/alan-turing
Buolamwini, J. (2019, February 7). Artificial intelligence has a problem with gender and racial bias. Here’s how to solve it. Time. https://time.com/5520558/artificial-intelligence-racial-gender-bias/
Chollet, F. (2019, November 5). On the measure of intelligence. https://arxiv.org/abs/1911.01547
Crawford, K. (2021). Atlas of AI. Yale University Press. (Introduction: pp. 1–21)
Hao, K. (2020, December 4). We read the paper that forced Timnit Gebru out of Google. Here’s what it says. MIT Technology Review. https://www.technologyreview.com/2020/12/04/1013294/google-ai-ethics-research-paper-timnit-gebru/
Harris, A. (2018, October 31). Languages vs. programming languages. Medium. https://medium.com/@anaharris/human-languages-vs-programming-languages-c89410f13252
Heilweil, R. (2020, February 18). Why algorithms can be racist and sexist. A computer can make a decision faster. That doesn’t make it fair. Vox. https://www.vox.com/recode/2020/2/18/21121286/algorithms-bias-discrimination-facial-recognition-transparency
McCarthy, J. (2007, November 12). What is artificial intelligence? http://jmc.stanford.edu/articles/whatisai/whatisai.pdf
OpenAI. (2024, June 2). ChatGPT response on AI pioneers and definitions of intelligence [Large language model output]. https://chatgpt.com/share/683e5a86-46f8-8012-a1c7-debc1ca0df51
Stonier, T. (1992). The evolution of machine intelligence. In Beyond information (pp. 121–138). Springer. https://doi.org/10.1007/978-1-4471-1835-0_6
Turing, A. M. (1950). Computing machinery and intelligence. Mind, 59(236), 433–460. https://doi.org/10.1093/mind/LIX.236.433
UBS. (n.d.). Meet the Nobel Laureates in economics: Do we understand human behaviour. https://www.ubs.com/global/en/wealth-management/chief-investment-office/our-research/discovering-economics/nobel-perspectives/herbert-simon.html
AI Artist Statement
In this IP, ChatGPT was only used to order my reference list above and to create the appropriately labelled responses for direct comparison. This includes the specific sections of my assignment where generative AI was directly integrated involved descriptions of Alan Turing, John McCarthy, Herb Simon, and Marvin Minsky, as well as my reflections comparing human and machine languages, intelligence, learning. Below is the original conversation with prompts and answers.
