[autokad]

I took the basics of a dream I had, and asked it to turn it into a short story. the result was pretty good. Is it using stuff already to seed its responses? sure, but thats what we do to. Nothing you do or say wasn't taught to you. But these are not simply parroting responses.

I said this to chatgpt: I had a dream that me and my friend were in a car accident, and we had a choice in deciding how to use 1 hour. we could use it to live out our last final moments or spend that hour on trying to think of a solution to survive the wreck. turn this into a short story.

As they sat trapped in their overturned car, Maria and her best friend Rachel had a dilemma. They only had one hour left to live and had to choose how to spend it. Rachel suggested they spend their final moments together, talking about all their favorite memories. But Maria had a different idea. She proposed they use the hour to think of a solution to survive the wreck. Rachel was hesitant at first, but ultimately agreed. For the next hour, they brainstormed every possible escape plan they could think of. They tried pushing against the doors, breaking the windows, and even attempting to signal for help. Just as they were about to give up hope, Maria remembered a tool in the trunk of the car. She crawled over to retrieve it and used it to pry open the door. Rachel followed her lead, and they finally escaped the car just in time. As they stumbled away from the wreck, both girls were in shock that they had made it out alive. They hugged each other tightly, grateful for the hour they spent trying to find a solution instead of giving up. From that moment on, they made a promise to never take a single moment for granted.

[tines]

> Nothing you do or say wasn't taught to you.

If nothing we do or say wasn't taught to us then where did all human knowledge come from in the first place? This doesn't hold up.

(Again, being direct for the sake of argument, please forgive any unkindness.)

[brycedriesenga]

From our environment, genetics, and other people. We simply are able to take in more inputs (i.e. not just text) than LLMs.

[pegasus]

I would agree that much more than we're usually ready to admit to ourselves is second-hand, but saying everything is going too far. Inventions and discoveries are happening all the time, at all scales.

[int_19h]

Inventions and discoveries are basically a very advanced form of pattern recognition - seeing "interesting" regularities in some particular input where no-one has spotted them before.

And LLMs are capable of making discoveries in this sense, if you feed them data and ask to spot the regularities. They're not particularly good at it, but that's a different question from whether they're able to do it in principle.

[pegasus]

Yes, in as far as LLMs can be said to make inventions and discoveries, this is clearly how they do it. And yes, these type of processes definitely play a big part in our human creative capacity. But to say this is all there is to it, is going too far in my opinion. We just don't know. There's still so much we don't understand about ourselves. We haven't designed ourselves after all, we just happened to "come to" one bright primeval day and since then we've been exploring and discovering ourselves. And again and again, we've found ourselves in that seductive spot where we thought we "got it" and there's nothing essential about ourselves we're still missing, only again and again to be proven wrong. Dogmas crumble, new dogmas coagulate, only to dissolve again. Or, we could use the more dignified word "paradigm".

[int_19h]

I mean, to me at least, that is the definition of discovery. The exact process used to spot the pattern is an implementation detail.

And yes, I agree that we really just don't know too many things. But my impression is that we're overestimating just how complicated out behavior really is.

[pegasus]

Yes, but that dream? It could never have it. Sure, it can produce at times very convincing descriptions of supposed dreams, but not actually have the experience of dreaming. Because of that, there will always be ways it will eventually miss-step when trying to mimic human narratives.