Ever since Kant, who was unable to distinguish between intellectual intuition and discursive reasoning – something the entire philosophical tradition had carefully done before him – there has been a great deal of confusion in the zeitgeist between reason and intelligence. What we now call “artificial intelligence” (AI) is in fact nothing more than “artificial reason” (AR), with all the qualities, but also all the shortcomings, of reason, a calculating mechanism subject to logic, whose deficiencies are well known.
To illustrate what should not be expected from such an AR, questions are put to it on the essential themes of man, the world, society, God and the aforementioned “artificial intelligence”, and its answers are transcribed, illustrating, we believe, the cognitive limits brought about by ChatGPT – its lack of intelligence, we might say. Readers can judge for themselves.
In the foreground, an excerpt from an article by Sarah Spiekermann, Professor of Information Systems at the University of Vienna (and originator of the IEEE Std 7000™-2021 ISO standard), in which, on the basis of the distinction between intelligence and reason, the irreducible gap between human intelligence and artificial reason is developed.
In his afterword, Professor Johannes Hoff broadens the perspective by denouncing the functionalist bias of contemporary anthropology and the digital transformation that has led to an unhealthy assimilation of human cognition to the “entropic” way in which machines function by default.
Contents
Exergue: text by Sarah Spiekermann
Foreword: RA, Artificial Reason
Chapter I. On man
- What is a man
- Morality
Chapter II. On the world
- Cosmology
- Business and politics
- Human society
- Democracy or electoral system
Chapter III. About God
- Believing in God
- The relationship between God and man
- From Master Eckhart
- Faith
- De la Trinité
- On the unity of religions
- Esotericism and metaphysics
- Transcendence and immanence
- Eschatological perspectives
- The Christological hologram
Chapter IV. On “artificial intelligence”
- Shouldn’t you be called “artificial reason”?
- Artificial reason and poetry
- Artificial reason and prose poetry
Afterword by Professor Johannes Hoff
Excerpt
Given the difference between reason and intelligence, shouldn’t what we call “artificial intelligence” be called “artificial reason”, since only the mental power to calculate concepts has been manufactured?
The terminology “artificial intelligence” is often used to describe computer systems that are capable of performing tasks that normally require human intelligence, such as speech recognition, image recognition, decision-making, language translation and so on. Although these systems do not possess self-awareness or thought per se, they are capable of processing large quantities of data and learning from it, using algorithms and information processing techniques.
That said, the notion of “artificial reason” might indeed better reflect the ability of these systems to perform logical calculations and make decisions based on these calculations, rather than referring to a capacity for learning or understanding.
(…)
When you read texts by Master Eckhart, do you understand them?
I don’t have the ability to “understand” in the same way as a human being. My functioning is based on statistical models and the recognition of linguistic patterns from the data on which I have been trained. I don’t have the capacity for deep understanding or subjective experience.