No Stupid Questions

Me:

You are a talented comedian. Generate some jokes or riddles that rely on wordplay.

ChatGPT 4:

Sure, here are a few wordplay-based jokes and riddles:

Why don’t scientists trust atoms? Because they make up everything!

I told my wife she should embrace her mistakes. She gave me a hug.

What do you call fake spaghetti? An “impasta.”

I’m reading a book on anti-gravity. It’s impossible to put down!

Why was the math book sad? Because it had too many problems.

Enjoy these light-hearted plays on words!

Edit: I prodded it a little, and I actually quite like the fourth one below.

Me:

These aren’t very clever. Can you generate some that a more mature audience would appreciate?

ChatGPT:

Of course, here are some more sophisticated wordplay-based jokes suitable for a mature audience:

Parallel lines have so much in common. It’s a shame they’ll never meet.

A Freudian slip is when you say one thing but mean your mother. I mean another.

I'm reading a book on the history of glue. Can't put it down, but I'm sticking to it.

Time flies like an arrow; fruit flies like a banana. A classic example of linguistic ambiguity.

The rotation of Earth really makes my day. Quite literally.

These jokes involve a bit more linguistic and conceptual play, appealing to an audience that enjoys a deeper level of wordplay.

Great video! Thanks for posting that

To be fair/to elaborate on that point, your dog is much much closer to human than chatgpt is, we share like 84% of DNA. Most of the same basic emotions like hunger, fear, desire, etc are present as well as the ability to learn and communicate.

Your dog may not be "scheming", because it lacks the ability to plan very far in the future, but it definitely has the intention of getting your attention and tries to figure out in the moment how to do it. Same as a human kid might do.

It is incredibly valuable to act like a dog is human, because dogs do actually share a lot of characteristics. Not all of course, it's still wrong to fully assume a dog is human, but as a quick heuristic it's still valuable a lot (84%? :D) of the time.

Yep, this is a very good explanation. Seeing ChatGPT "talk" is immediately associated with sentience, because for your entire life, and millions of years of evolution, apeech was in 99.9% of cases, a sign of aentience. So your brain doesn't even consider it a question, until you consciously stop to think about it.

An interesting way to antromorphizise GPT that's still technically correct is to think of it as having essentially perfect memory. So it doesn't know how to talk, but it has seen so many conversations (literal trillions) that it can recognize the patterns that make up speech and simply "remember" what the most likely combination of words is, given the context, with zero actual "understanding" of language. (Human trainers then fine-tune these guesses to give you the ChatGPT experience)

Just to make clear because it seems to come up a lot in some responses - I absolutely don't think (and never have) that chatgpt is intelligent, 'understands' what I'm saying to it or what it's saying to me (let alone is accurate!). Older chat bots were very prone to getting in weird loops, or sudden context/topic switches. Chatgpt doesn't do this very often, and I was wondering what the mechanism for keeping it's answers plausibly connected to the topic under discussion and avoiding grammatical cul-de-sacs.

I know it's just a model, I want to understand the difference between it's predictions and the predictions on my Android keyboard. Is it simply considering the entire previous text as it makes its predictions vs just the last few words? Why doesn't it occasionally respond with a hundred thousand word response? Many of the texts it's trained on are longer than it's usual responses. There seems to be some limits and guidance given either through its training data or its response training that guide it beyond "based on the texts I have seen, what is the most likely word." and I was curious if there was a summary what the blend of corpus based prediction and respinse feedback, etc. has been used.

Try to use it to solve a difficult problem and it will become extremely obvious that it has no idea what it is talking about.

The magic sauce is context length within reasonable compute restraints. Phone predictive text has a context length of like 2-3 words, ChatGPT (and other LLMs) have figured out how to do predictions on thousands or tens of thousands of words of context at a time.

I think this explanation would be more satisfying if we had a better understanding of how the human brain produces intelligence.

This is very interesting, thanks

That's really helpful! Exactly the sort of thing I was looking for. I wasn't aware of the role of temperature and embedding, thet explain a lot.

To be fair, I think most people do that too. Not a lot of thought out there.

Thank you for sharing this. I just finished watching it.