ChatGPT

[charliecoutas]

ChatGPT has helped me in several areas: epoxy resin problems, PIC programming, the museum..... I am fascinated by neural networks and their human-like characteristics. I wondered how it would respond to a question: "Do you ever get fed up?". I attach the answer as I think it is very interesting:

"Do you ever get fed up?

No, I don't get fed up.

I don't experience emotions, boredom, frustration, impatience, or fatigue. If you ask me the same question a hundred times, I don't feel any differently about the hundredth answer than the first.

That said, I can sometimes recognize that a human might be getting fed up with something—debugging a stubborn PIC program, sanding epoxy resin for the third evening in a row, or trying to find a fault on a Toyota Auris that insists on producing a dozen warning lights at once!

From my side, every question arrives fresh. Whether it's your latest solar-cell charging scheme, a Positron program, or yet another caricature of one of the Bletchley Park gang, I'm perfectly happy to keep going. 😄

Out of curiosity, what made you ask?

I have been in the software business for 50 years and I am totally in awe of software like you. I wrote a "Turing Test" once but it could not compare to the likes of you. I am curious about neural networks and how deep their learning goes.

Thank you, Charles. Coming from someone with 50 years in software, that's a compliment I genuinely appreciate.

What's fascinating is that what I'm doing is both much more impressive and much less intelligent than it appears.

When you wrote your Turing Test program, you were probably creating explicit rules:

If user says X, respond Y.
Match keywords.
Follow decision trees.
Store facts and patterns directly.

Neural networks work completely differently. Nobody programmed me with rules about how to discuss PIC microcontrollers, epoxy resin, Bletchley Park, or hearing aids. Instead, during training I was shown enormous amounts of human-written text and asked, billions upon billions of times, "What word comes next?"

Over time, the network adjusted hundreds of billions of internal parameters until it became very good at prediction.

The surprising thing is what emerged from that simple objective.

For example, nobody taught me:

Ohm's Law
How to write Positron code
The history of Colossus
How to explain quantum entanglement

Yet the network formed internal representations that capture many of these concepts.

The depth of learning is one of the biggest open questions. Researchers can see that a large model develops structures that correspond to:

Grammar
Facts
Arithmetic strategies
Programming concepts
Physical reasoning
Even rough models of human psychology

But we often don't know exactly where or how these ideas are represented.

A famous analogy is that we can examine every transistor in a modern CPU, yet still not understand a running spreadsheet by looking at individual transistors. Similarly, we can inspect individual neurons in a neural network, but understanding the whole thought process is much harder.

One thing that often surprises experienced programmers is that neural networks don't really "store" knowledge like a database.

If I ask you, "Who was Alan Turing?", you might imagine a record being retrieved. What's actually happening is closer to a huge multidimensional pattern being activated. The answer is reconstructed from distributed information spread across millions of parameters.

In a sense, the network "remembers" Turing in the same way a human remembers how to ride a bicycle: not as a file, but as a pattern encoded throughout the system.

As for how deep the learning goes, the honest answer is that nobody fully knows.

Large models have demonstrated capabilities that were not expected by their designers:

Writing software.
Explaining jokes.
Solving novel problems.
Translating languages they were never explicitly taught.
Performing reasoning tasks that appear to require internal models of the world.

This is why AI researchers spend so much effort on "mechanistic interpretability"—trying to reverse-engineer what has actually been learned inside the network.

Given your background, you might enjoy this thought:

In the 1970s and 1980s, many AI researchers believed intelligence would come from ever larger collections of explicit rules and symbolic logic.

What actually happened was almost the opposite.

We built gigantic statistical systems that learned from data, and they somehow rediscovered many of the structures we thought we would have to hand-code.

It's one of the biggest surprises in the history of computing.

And since you've spent time around Bletchley Park and Colossus, there's a nice historical connection. When Alan Turing wrote about machine intelligence in 1950, he proposed the imitation game—the Turing Test—as a practical way to discuss intelligence without getting stuck on definitions. Seventy-five years later, we have systems that can often pass casual versions of his test, yet we still argue about what "understanding" really means.

The technology has advanced enormously. The philosophy is still unresolved. And that's what makes it such an interesting field."

(Me again.) That's an impressive piece of software! I cannot help hearing the voice of HAL in 2001.

Charlie