Can AI possess intuition?

[tonychanyt]

Prof Daniel Dennett said:

Herbert Dreyfus said they'd never make a computer with intuition. No computer program can have intuition.

Dreyfus didn't think an AI could have intuition.

It's child's play to make a computer that has intuition. You take any computer program that solves any problem you like. It may be long division, weather prediction or whatever, and you ask it a question and it gives you an answer. You say, "How did you work out that answer?" It says, "I don't know. It just came to me.

The audience laughed but I do not find that funny. That's a trivialization of intuition and it is not helpful toward a serious investigation of intuition. Then Dennett contradicted himself:

Intuition is when you've got a conviction and you haven't the faintest idea how you got it.

But according to his own definition, the computer program can trace its steps of long division and explain its logic to the asker as AI chats like Qwen can do today.

Can an AI simulate intuition?

Yes, according to Dennett's trivial example.

Can an AI possess real intuition?

How do people recognize one another? We do it intuitively, without consciously analyzing a person's facial features. Similarly, AI can perform pattern recognition using vector-based models without requiring a step-by-step analysis of facial characteristics to reach a conclusion. A deep learning model trained on millions of medical images can "intuitively" identify diseases in new images by recognizing subtle patterns. In this regard, AI demonstrates a form of pattern recognition intuition.

In contrast, an AI chess player can make moves that appear intuitive to human observers, yet they are actually based on analyzing move-by-move contingencies, looking 10 moves ahead. If you ask why it makes a specific move, it can trace its reasoning and explain its steps.

Another type of intuition relies on heuristics. For instance, when presented with two different answers, the simpler one is likely correct. For another example, when someone tells me that he is a jazz player, I immediately think of a saxophone. Of course, my intuition could be wrong. AI can utilize heuristics similarly.

What other kinds of human intuition are there? Can an AI replicate them all?

Can an AI have intuition?

Today's AI possesses some aspects of human intuition already. Perhaps in the future, AI can develop the full spectrum of human intuition. I don't know.

 

[Richard T]

I'm thinking they can't have an inner knowing. AI is more like Spock, emotions and irrational thinking do not seem to be present.

 

[SelfSim]

Prof Daniel Dennett said:


Dreyfus didn't think an AI could have intuition.


The audience laughed but I do not find that funny. That's a trivialization of intuition and it is not helpful toward a serious investigation of intuition. Then Dennett contradicted himself:


But according to his own definition, the computer program can trace its steps of long division and explain its logic to the asker as AI chats like Qwen can do today.

Can an AI simulate intuition?

Yes, according to Dennett's trivial example.

Can an AI possess real intuition?

How do people recognize one another? We do it intuitively, without consciously analyzing a person's facial features. Similarly, AI can perform pattern recognition using vector-based models without requiring a step-by-step analysis of facial characteristics to reach a conclusion. A deep learning model trained on millions of medical images can "intuitively" identify diseases in new images by recognizing subtle patterns. In this regard, AI demonstrates a form of pattern recognition intuition.

In contrast, an AI chess player can make moves that appear intuitive to human observers, yet they are actually based on analyzing move-by-move contingencies, looking 10 moves ahead. If you ask why it makes a specific move, it can trace its reasoning and explain its steps.

Another type of intuition relies on heuristics. For instance, when presented with two different answers, the simpler one is likely correct. For another example, when someone tells me that he is a jazz player, I immediately think of a saxophone. Of course, my intuition could be wrong. AI can utilize heuristics similarly.

What other kinds of human intuition are there? Can an AI replicate them all?

Can an AI have intuition?

Today's AI possesses some aspects of human intuition already. Perhaps in the future, AI can develop the full spectrum of human intuition. I don't know.

Interesting ..

I asked Google's AI: 'Explain human intuition'. The response was:

Human intuition is the ability to understand something instinctively, without conscious reasoning, often described as a "gut feeling" or "knowing" without needing an explanation. It's thought to arise from rapid unconscious pattern matching of past experiences and current situations.

Then I asked it: 'Explain human counter-intuition in ai'

Human counter-intuition in AI refers to situations where AI systems, despite being trained on vast datasets, arrive at conclusions or make decisions that seem illogical or counter to human expectations, often because they are focusing on patterns that humans might overlook or deem irrelevant.

 

[Richard T]

Interesting ..

I asked Google's AI: 'Explain human intuition'. The response was:

Human intuition is the ability to understand something instinctively, without conscious reasoning, often described as a "gut feeling" or "knowing" without needing an explanation. It's thought to arise from rapid unconscious pattern matching of past experiences and current situations.

Then I asked it: 'Explain human counter-intuition in ai'

Human counter-intuition in AI refers to situations where AI systems, despite being trained on vast datasets, arrive at conclusions or make decisions that seem illogical or counter to human expectations, often because they are focusing on patterns that humans might overlook or deem irrelevant.

Nice post. The AI answer is crafted in deceit from what I read. making decisions illogical to humans, yet still focused on patterns or datasets that human would overlook. To me that is not intuition, it is just superior logical reasoning. A computer would never bet against the mathematical odds. i think though at some point they could be trained to find a human tell based on patterns of behavior. Would they ever call a hand though based on intuition? I'm thinking not.

 

[SelfSim]

Nice post. The AI answer is crafted in deceit from what I read. making decisions illogical to humans, yet still focused on patterns or datasets that human would overlook. To me that is not intuition, it is just superior logical reasoning. A computer would never bet against the mathematical odds. i think though at some point they could be trained to find a human tell based on patterns of behavior. Would they ever call a hand though based on intuition? I'm thinking not.

I'm a little wary of this AI. On statistical inferences vs human intuitive motivations, it goes on to explain in more detail:

• AI's Data-Driven Nature:
  AI, particularly machine learning models, learns by identifying patterns and relationships within data. This means that if the training data is biased or incomplete, the AI model might learn and generalize these biases, leading to counter-intuitive results.
• Focus on Statistical Correlations:
  AI models often excel at finding statistical correlations, even if those correlations don't represent true causal relationships. This can lead to AI making decisions based on superficial or irrelevant factors that humans would intuitively disregard.

Its interesting that its been fairly honest about its own biases/incompletion in point (i) and then explains how it disregards mistaken irrelevancies in (ii).

 

[Larniavc]

Prof Daniel Dennett said:


Dreyfus didn't think an AI could have intuition.


The audience laughed but I do not find that funny. That's a trivialization of intuition and it is not helpful toward a serious investigation of intuition. Then Dennett contradicted himself:


But according to his own definition, the computer program can trace its steps of long division and explain its logic to the asker as AI chats like Qwen can do today.

Can an AI simulate intuition?

Yes, according to Dennett's trivial example.

Can an AI possess real intuition?

How do people recognize one another? We do it intuitively, without consciously analyzing a person's facial features. Similarly, AI can perform pattern recognition using vector-based models without requiring a step-by-step analysis of facial characteristics to reach a conclusion. A deep learning model trained on millions of medical images can "intuitively" identify diseases in new images by recognizing subtle patterns. In this regard, AI demonstrates a form of pattern recognition intuition.

In contrast, an AI chess player can make moves that appear intuitive to human observers, yet they are actually based on analyzing move-by-move contingencies, looking 10 moves ahead. If you ask why it makes a specific move, it can trace its reasoning and explain its steps.

Another type of intuition relies on heuristics. For instance, when presented with two different answers, the simpler one is likely correct. For another example, when someone tells me that he is a jazz player, I immediately think of a saxophone. Of course, my intuition could be wrong. AI can utilize heuristics similarly.

What other kinds of human intuition are there? Can an AI replicate them all?

Can an AI have intuition?

Today's AI possesses some aspects of human intuition already. Perhaps in the future, AI can develop the full spectrum of human intuition. I don't know.

Intuition is really only arriving at a conclusion without knowing exactly why. Or arriving at an emotionally congruent conclusion.

I would hypothesis an AI couldn’t do that.

 

[tonychanyt]

Intuition is really only arriving at a conclusion without knowing exactly why.

When an AI uses a vector space black box model, it cannot explain why it arrives at a conclusion.

 

[SelfSim]

When an AI uses a vector space black box model, it cannot explain why it arrives at a conclusion.

Please explain what you mean by a 'vector space black box model'.

Is it the same as a neural network (ie: optimization algorithms)?

 

[johansen]

Can an AI robot dowse for water?

What about natural gas, and electrical lines? -or any other object of natural material to be searched for?
Does it have to use copper rods or will wood sticks work?

Please explain what you mean by a 'vector space black box model'.

Is it the same as a neural network (ie: optimization algorithms)?

I dont think Tony actually knows anything about this beyond generating posts that sound spiritual, with chat gpt.

Computers are a long series of 1s and 0s.

You store all the information generated in the process of an ai engine and you can get the exact same answer twice.
In real life this may be near impossible due to random number generators in the hardware of processors themselves, so you would have to re compile the ai engine to use a publically observable algorithm and data processing system.. which would slow it down quite a lot, but you would get the same answer every time if all the conditions are met and are the same.

That being said certain people said 20 years ago that the beast of revelation is a demon possessed ai computer. This is not new.


When i read ai content, it often "sounds to me" like a demon.

 

[SelfSim]

Folks if we're going to discuss how AI explains its conclusions, in order for us to be singing off the same plate, I highly recommend reviewing this post in a recent thread, where Open AI and DeepSeek AI, themselves, provide explanations .

No offence intended here, but thus far in this thread, the explanantions of AI are too superficial and underestimate the current sophistication of their neural networks/optimisation techniques and how they are used in both their training, (knowledge acquisition), decision making and interpretational processes.

They aren't perfect, I agree .. but they're far from just CPUs executing fixed instructions based on binary based Boolean Algebra and assembler codes.

 

[Larniavc]

When an AI uses a vector space black box model, it cannot explain why it arrives at a conclusion.

That’s because it’s not conscious. A calculator cannot do that either. It cannot opine on it’s own existence.

 

[Warden_of_the_Storm]

I would definitely say no, AI cannot possess intuition.

 

[tonychanyt]

I would definitely say no, AI cannot possess intuition.

Define intuition

 

[Warden_of_the_Storm]

Define intuition

... why should I define intuition?

 

[Warden_of_the_Storm]

I really do not understand why I need to define the word intuition to support my claim that AI cannot possess.

Anyone commenting on this thread knows what intuition means. The OP of the thread knows what intuition means.

Why do I need to define it to support my claim?

 

[SelfSim]

I really do not understand why I need to define the word intuition to support my claim that AI cannot possess.

Anyone commenting on this thread knows what intuition means. The OP of the thread knows what intuition means.

Why do I need to define it to support my claim?

It appears to be a game of: 'Anyone who uses science to rule out my belief is a proponent of scientism .. not science'.
In my view, how you, or I define intuition is irrelevant. How AI describes its arriving at its conclusions is the issue, yet there has been zero interest shown for attaining that understanding.

I conclude its all about using a belief to rule out other people's beliefs, whilst the proponent (the OP) doesn't seem to recognise, (or understand), the scientific method when its being followed ... (thereby mistaking science as being a belief system).

 

[dlamberth]

I asked ChatGPT if AI has intuition. Basically, it said, it's more like "advanced pattern recognition than true intuition."
Here's the full answer given...

AI doesn’t have intuition in the way humans do. Intuition, for people, is often described as a "gut feeling" or an understanding of something without conscious reasoning. It’s tied to our experiences, emotions, and subconscious processing.

AI, on the other hand, operates based on data and algorithms. It doesn’t have feelings or subjective experiences, so it doesn’t “feel” its way through problems. However, AI can sometimes appear to exhibit something similar to intuition because it can identify patterns in data that might not be immediately obvious to a human. This is especially true in advanced machine learning models, which can make predictions or decisions that seem insightful or intuitive based on large amounts of data they've been trained on.

So, while AI can seem to make intuitive decisions, what it’s actually doing is applying complex calculations and statistical models to produce its answers. It's more like advanced pattern recognition than true intuition.

 

[SelfSim]

I asked ChatGPT if AI has intuition. Basically, it said, it's more like "advanced pattern recognition than true intuition."
Here's the full answer given...

AI doesn’t have intuition in the way humans do. Intuition, for people, is often described as a "gut feeling" or an understanding of something without conscious reasoning. It’s tied to our experiences, emotions, and subconscious processing.

AI, on the other hand, operates based on data and algorithms. It doesn’t have feelings or subjective experiences, so it doesn’t “feel” its way through problems. However, AI can sometimes appear to exhibit something similar to intuition because it can identify patterns in data that might not be immediately obvious to a human. This is especially true in advanced machine learning models, which can make predictions or decisions that seem insightful or intuitive based on large amounts of data they've been trained on.

So, while AI can seem to make intuitive decisions, what it’s actually doing is applying complex calculations and statistical models to produce its answers. It's more like advanced pattern recognition than true intuition.

You should ask how does AI conclude that is comparative basis of 'a true' intuition actually exists?
How is AI's advanced pattern recognition not a true intuition?

 

[SelfSim]

You should ask how does AI conclude that is comparative basis of 'a true' intuition actually exists?
How is AI's advanced pattern recognition not a true intuition?

Meh .. I did it myself. Its answers are:

Q: How is AI's advanced pattern recognition not a true intuition?
i) While AI excels at pattern recognition, it lacks the subjective, emotional, and contextual understanding that characterizes human intuition, making its abilities fundamentally different. AI's pattern recognition is based on data and algorithms, while human intuition involves experience, emotions, and a broader understanding of the world.

ii) AI's pattern recognition, while impressive, isn't true intuition because it lacks understanding, context, and the ability to reason with meaning, relying instead on statistical probabilities and pre-existing data, whereas intuition involves genuine comprehension and creative insight.

 

[dlamberth]

How is AI's advanced pattern recognition not a true intuition?

Here's what ChatGPT has to say:

AI's advanced pattern recognition might seem similar to human intuition at times, but they are fundamentally different in nature. Here's why:

1. Mechanistic vs. Cognitive:​

• AI Pattern Recognition: AI uses statistical methods to detect patterns based on vast amounts of data. It doesn’t "understand" the data in the same way humans do. It relies on algorithms to optimize outcomes based on input data, like recognizing patterns in images, sounds, or text, but without any real comprehension of the context or meaning.
• Human Intuition: Intuition in humans is more than just pattern recognition. It’s often the result of a combination of conscious learning, subconscious knowledge, emotions, experiences, and a deeper, sometimes inexplicable, "gut feeling" that guides decisions. Human intuition is more subjective and not solely dependent on processing large amounts of data.

2. Data Dependency:​

• AI: AI requires data to function and improve. The more data it has, the better it can recognize patterns and make predictions. However, if AI is confronted with a situation or data outside of its training, it struggles and cannot "feel" its way through new experiences like humans can.
• Humans: Human intuition can often make leaps of logic or sense out of limited information. Humans are capable of reasoning through situations even without all the data, filling in gaps with personal knowledge and experience. Intuition is also shaped by emotional intelligence, which AI currently doesn't possess.

3. Context Awareness:​

• AI: AI can recognize patterns but may not fully understand the context. It can, for instance, recognize a face but not know the emotional context behind that face. It lacks a true understanding of social, historical, or emotional contexts that influence human intuition.
• Humans: Intuition in humans is deeply embedded in a wider context, influenced by cultural, emotional, and personal experiences. It’s not just recognizing a pattern, but also understanding the "why" behind that pattern and what it might imply in a given situation.

4. Consciousness and Experience:​

• AI: AI does not have consciousness or personal experiences. It lacks the internal "sense" that humans have when they feel something is right or wrong, or when they instinctively understand a problem.
• Humans: Intuition is informed by personal experiences, emotions, and a consciousness of being. This makes human intuition rich, nuanced, and capable of integrating a wide range of factors beyond mere data.

5. Flexibility and Creativity:​

• AI: While AI can produce creative outputs (like generating art or writing), its creativity is based on recombining existing patterns rather than creating something entirely new from a place of deep, novel insight.
• Humans: Human intuition can involve original thought, creative leaps, and solving problems in entirely new ways. It’s not always based on prior data or experience, and humans can feel their way into unfamiliar situations, adapting more fluidly to change.

In Conclusion:​

AI's pattern recognition is incredibly powerful and can mimic intuition in some ways, especially in structured tasks. But it lacks the depth, context, and subjective qualities of human intuition. It’s driven by algorithms and data, whereas intuition is a multifaceted process that involves emotions, experience, and a complex understanding of context.