[oxfordmale]

You know what a book is and can reason about it. As a human you can provide answers that go beyond the knowledge you have ingested.

For example, if you ask ChatGPT if books can be fluorescent it says no. However, as an adult you know someone somewhere has made a book with fluorescent images, as it is a cool thing. You are combining knowledge from two different fields (books + fluorescence) and establishing the likelihood of someone being able to combine them.

[ai-punter]

lol, really?

Me: Can books be fluorescent?

GPT-4: While the term "fluorescent" is typically used to describe substances that can absorb light and then re-emit it, often at a different wavelength, there's no inherent reason why a book couldn't be made with fluorescent properties.

This could be achieved by using fluorescent ink, dyes, or paints on the cover or the pages, or by incorporating fluorescent fibers into the paper itself. When exposed to ultraviolet light (often called "black light"), these materials would glow. This might be used for aesthetic reasons, for practical reasons like aiding reading in low-light conditions, or for interactive elements in children's books or art books.

It's important to note that this is not a common feature for most books, as it would increase production costs and might not be appealing or necessary for all readers or all types of books. Also, long-term exposure to ultraviolet light can be damaging to many types of paper and ink, which could reduce the lifespan of the book.

As of my knowledge cutoff in September 2021, I don't have any specific examples of fluorescent books, but that doesn't mean they don't exist or couldn't be created.

[oxfordmale]

This exactly illustrates the problem of ChatGPT. I asked the same question, phrased slightly differently, and it said no. It also not unlikely my question was used to train CHATGPT further.

[9dev]

Does it, really? I’m pretty sure if you’d ask some people, there are going to be some that’d answer „no“ too.

Besides, you’re shifting the goalposts as you go, altering your arguments as it suits your view. The parent comment just disproved your entire point how LLMs cannot combine different fields - and now you just pick a different angle altogether. Maybe take a step back and reconsider your opinions?

[pcthrowaway]

ChatGPT is GPT3.5 isn't it? The other person was using GPT4.

[jasmer]

Different answers at different times, seems very human to me :)

[divan]

Yet, this doesn't answer my question. Human brain is obviously has so much more in it (visual cortex for starters, grid cells etc), and, in terms of neural network, much more sophisticated architecture. But still, there is a big probability that what we call "knowledge" and "reasoning" and "conciousness" are just a result of this sophisticated architecture. I.e. there is no special magical thing for "reasoning" that next generations of prediction models can't replicate.

There is a faboulous book by Jeff Hawkins "On Intelligence" (2004) that explores this. I think main premise of it still holds true: brain is "just" a highly sophisticated hierarchical tissue whose main job is to extract patterns and make predictions. Fundamentally it doesn't seem very different from what LLMs are.