[Drawn to my attention by John Siegrist on this blog from Felix Hovespian https://www.linkedin.com/feed/update/urn%3Ali%3Aactivity%3A7193830352144977920/?commentUrn=urn%3Ali%3Acomment%3A%28activity%3A7193830352144977920%2C7193839932258353152%29&dashCommentUrn=urn%3Ali%3Afsd%5Fcomment%3A%287193839932258353152%2Curn%3Ali%3Aactivity%3A7193830352144977920%29&replyUrn=urn%3Ali%3Acomment%3A%28activity%3A7193830352144977920%2C7194207491482615809%29&dashReplyUrn=urn%3Ali%3Afsd%5Fcomment%3A%287194207491482615809%2Curn%3Ali%3Aactivity%3A7193830352144977920%29 ]

John McCarthy Tue Jun 13 03:06:03 PDT 2000
https://www-formal.stanford.edu/jmc/reviews/bloomfield/bloomfield.html
(From his interesting and very 90s website https://www-formal.stanford.edu/jmc/)

pdf of the same: http://jmc.stanford.edu/artificial-intelligence/reviews/bloomfield.pdf

A book review, in which he says

Schopman mentions many influences of earlier work on AI pioneers. I can report that many of them didn’t influence me except negatively, but in order to settle the matter of influences it would be necessary to actually ask (say) Minsky and Newell and Simon. As for myself, one of the reasons for inventing the term “artificial intelligence” was to escape association with “cybernetics”. Its concentration on analog feedback seemed misguided, and I wished to avoid having either to accept Norbert (not Robert) Wiener as a guru or having to argue with him. (By the way I assume that the “Walter Gibbs” Schopman refers to as having influenced Wiener is most likely the turn-of-the-century American physicist Josiah Willard Gibbs, though possibly McCulloch’s colleague Walter Pitts). Minsky tells me that neither Wiener nor von Neumann, with whom he had personal contact, influenced him, because he didn’t agree with their ideas. He does mention influence from Rashevsky, McCulloch and Pitts.

__
On his own thread, Felix Hovespian had responded:

“Most of what is called hashtag#artificialIntelligence today is based on 1st order hashtag#cybernetics, and therefore it’s very like hashtag#behaviorism.

It doesn’t take into account what the intelligence has to do in order to hashtag#observe, to construct, to hashtag#think … ”

[ Ernst von Glasersfeld and a History of Cybernetics,
https://youtu.be/pm5u68t6kPI ]

___
Various tweets on this point (turns out’Grok’ is an actually useful search engine for twitter – hurrah!) – all coming back to the same quote:

Apr 19 2022 Alex Dimakis

May 5 2023 Eryk Salvaggio

Jan 21 2024 Meredith Whittaker

_____________

A couple of useful-looking LLM summaries of the differences:

ChatGPT:
John McCarthy, a pivotal figure in the development of artificial intelligence, had several key differences with the field of cybernetics, particularly concerning the methods and goals of research in understanding and creating intelligent systems. Here are the main areas where McCarthy’s views diverged from those predominant in cybernetics:

### 1. **Focus on Symbolic Processing:**
– McCarthy was a strong proponent of symbolic AI, which emphasizes the manipulation of symbols to perform reasoning tasks. He believed that intelligence could be described as symbol manipulation and that machines could be made intelligent by programming them to manipulate symbols according to formal rules.
– Cybernetics, in contrast, focused more broadly on communication and control in animals and machines, often considering feedback mechanisms and homeostatic systems rather than specific computational models of intelligence.

### 2. **Theoretical Foundations:**
– McCarthy was instrumental in developing the theoretical foundations of computing and artificial intelligence, emphasizing formalisms such as recursion theory and the use of formal logic to model intelligent behavior. His approach was more mathematical and abstract, rooted in formal logic and computation theory.
– Cybernetics tended to be more interdisciplinary and system-oriented, involving fields like biology, engineering, and psychology, and often focused on practical applications rather than abstract computation.

### 3. **Methodological Differences:**
– McCarthy’s approach in AI research was to create an environment where artificial agents could perform tasks by thinking, using heuristic methods to solve problems. This approach was quite different from the cybernetic focus on systems dynamics, feedback loops, and regulatory mechanisms.

### 4. **AI vs. Cybernetics Communities:**
– During the 1950s and 1960s, as AI emerged as a distinct field, there was a notable division between the AI community and the cyberneticians. McCarthy, who coined the term “Artificial Intelligence” and organized the famous Dartmouth Conference in 1956, was part of shaping AI as a field that, in some ways, defined itself in opposition to cybernetics. AI was seen as focusing on creating intelligent machines, whereas cybernetics was seen as more concerned with understanding systems, including but not limited to intelligent behavior.

### 5. **Philosophical Disagreements:**
– McCarthy often expressed skepticism about some of the philosophical stances that were sometimes associated with cybernetics, such as overly broad interpretations of system theory or the applicability of cybernetic principles to all aspects of human knowledge and activity.

Despite these differences, both McCarthy’s work in AI and the broader field of cybernetics have contributed foundational concepts to the understanding of complex systems and intelligent behavior. The development of AI has since embraced many cybernetic principles, particularly in areas like neural networks and autonomous robots, showing that the fields have potential for convergence despite their initial distinctions.
_____________
Gemini:
John McCarthy, one of the founding fathers of Artificial Intelligence (AI), had several key differences with cybernetics:

1. **Focus on Symbol Manipulation:** McCarthy believed that the essence of intelligence lay in the manipulation of symbols and that creating intelligent machines required a way to represent and process abstract concepts. In contrast, cybernetics focused on feedback loops, control systems, and the study of communication within natural and artificial systems.

2. **Disinterest in Biological Models:** McCarthy was less interested in replicating biological processes as a route to intelligence. Cyberneticists like Norbert Wiener and Warren McCulloch were explicitly interested in understanding biological systems (like the brain) and applying those principles to engineering.

3. **Top-Down vs. Bottom-Up Approach:** McCarthy argued for a top-down approach to AI, focusing on developing high-level cognitive functions like reasoning and problem-solving. Cybernetics often took a more bottom-up approach, interested in understanding and building self-organizing systems that could adapt and learn.

4. **Artificial vs. Augmented Intelligence:** McCarthy aimed to build wholly artificial intelligent systems, independent of human control. Parts of cybernetics focused on augmenting human intelligence and the connection between humans and machines.

5. **Distinct Terminology:** McCarthy coined the term “Artificial Intelligence” in 1955, intentionally distinguishing his work from the existing field of cybernetics. This reflected his desire to create a new discipline focused on the specific goals of building intelligent machines.

**In Summary:**

While both fields shared a common interest in systems, information, and how machines process them, McCarthy’s work in AI aimed to break away from the more biologically focused cybernetics movement. He sought a more abstract, symbolic approach to create independent intelligent entities.
___

[I don’t expect to be in the habit of doing ‘AI’ summaries, but it seemed relevant here 😉 – and I didn’t easily find other quick sources summarising etc…]