> And yet these systems are incapable of genuine creativity.
Define "genuine creativity".
Define "genuine creativity".
Genuine creativity, often attributed to humans, is the ability to generate, imagine, or invent something new and original that has value or meaning. It involves thinking beyond existing boundaries, making connections between different pieces of information, and coming up with innovative solutions to problems.
Creativity can manifest in many forms, including:
Artistic creativity: This is often the first thing people think of when they hear the word "creativity". It includes creating visual art, music, literature, and more.
Inventive creativity: This involves coming up with new products, technologies, or methods that solve problems in novel ways.
Conceptual creativity: This involves developing new theories, models, or ways of understanding the world.
Problem-solving creativity: This involves finding unique solutions to challenges or problems.
Genuine creativity is often characterized by originality, expressiveness, and the ability to transform or redefine existing ideas or norms. It's a complex process that involves both conscious and unconscious thinking, and it's influenced by a person's knowledge, experiences, personality, and environment.
I went a step further and asked if it's capable of genuine creativity and received:
As an AI, I don't possess creativity in the human sense. I don't have feelings, thoughts, or experiences, and I don't generate ideas or concepts spontaneously. However, I can generate unique combinations of information based on the vast amount of data I've been trained on. This can sometimes appear as "creativity", but it's important to note that it's a result of complex algorithms and computations, not genuine creative thought.
My terse reply actually indicates an understanding that we completely lack a formal definition of "genuine creativity", and therefore any such claims are vague intuitions at best.
> I don't have feelings, thoughts, or experiences
This implicitly assumes we have a mechanistic understanding of feelings, thoughts or experiences. We don't, therefore we can make no such definitive claims about how machine learning and human cognitive processes. ChatGPT has specifically been trained to give this response despite agreeing with an argument that suggests it could indeed have mental states:
https://twitter.com/naasking/status/1598802001428566016
> As an AI, I don't possess creativity in the human sense. I don't have feelings, thoughts, or experiences, and I don't generate ideas or concepts spontaneously
Define "spontaneously". If you mean that humans act without apparent cause, that does not entail there is no cause. If there is a cause, then that cause can be modeled as an input into a pure function. ChatGPT and other ML systems are pure functions can also mix concepts and generate new and unique outputs from its learned state space given such inputs. Humans are still more complex than such systems, so the mystique can hide in the perceived complexity, but don't mistake this for a different kind of process. Which isn't to say that it is the same process, I'm saying there's no real basis for either claim.
I think there's a lot of sloppy thinking going on when comparing human brains and ML, particularly ascribing some sort of exceptionalism to humans. There's a long, incorrect history of that.
These sorts of clipped sentences without any supporting context are understood to be delivered in bad faith. If you want to discuss in good faith, then elaborate. From here it sure looks like you wanted to score points by derailing the discussion on what you’ve deemed to be poor word choice.
you've been called and it turns out your argument was merely a bluff
I viewed the curt demand I provide a definition as rude and a cheap tactic intended to disrupt a discussion. And the ensuing discussion with that particular person did nothing to convince me otherwise. Fortunately, I don’t owe them a reply and you don’t have to believe me. It’s all good.
The fact that it knows the definition of creativity makes it's answer suspect. It's like saying this: "I am not capable of speaking or understanding English, what you see here is just a statistical prediction of the next most likely words. I do not in actuality understand or speak English."
Basically it's a best fit curve in N-dimensional space. The entire human brain can be modeled this way. In practice what we end up doing is using a bunch of math tricks to try to poke and prod at this curve to get some sort of "fit" on the data.
There are an infinite number of possible curves that can fit within this data. One of these curves is the LLM. The other curve is the human brain.
Here's a better way to put it. Your entire OS can be modeled under this idea. We can use a bunch of training data and basically recreate your operating system under ML. Just feed in current state and train it until it will output correct state.
But understanding the OS from this ML perspective is a far cry from understanding the OS from the perspective of source code.
We do NOT understand fully what's going on. In fact, the fact that the LLM even had chatGPT's capabilities was not predicted or foreseen.