The video shows an answer being written out using some sort of animation technique to give it a dramatic effect. Looks gimmicky.

guys... should we tell him?

Tell him what? It is annoying that they don't return the output instantly. This does throttle usage, so I can see why they do it, but it is annoying.

I asked ChatGPT about this:

"Why are ChatGPT responses written a few words at a time?"

It replied, a few words at a time:

- - -

The responses are broken up into smaller chunks for several reasons:

1. Better readability: Breaking up the responses into smaller pieces makes it easier for users to read and understand the information being provided.

2. Interactivity: ChatGPT's response format allows for a back-and-forth interaction with the user, making it feel more like a conversation and allowing the user to ask follow-up questions or clarify information.

3. Error correction: By responding a few words at a time, the model can quickly correct any errors or misunderstandings in real-time, leading to a more accurate overall conversation.

4. Efficient communication: Responding in smaller chunks allows the model to quickly provide information and reduces the latency in the communication process.

Overall, the goal is to create an efficient, user-friendly, and interactive conversational experience.

Yes, a great example of bullshit from ChatGPT.

For those who don't know, it is like Markov Chains: probability of next word (or a group of words encoded as a token) is calculated based on previous words and computationally intensive. It just uses not just probability between 1-2 previous tokens, it uses 2048 token window (roughly 1500 words) to predict next token, then puts next token into window and goes on.

What is even the point of posting nonsense spam from ChatGPT as replies? At least clearly indicate that it's generated. I thought it was from OpenAI as you said "from the horse's mouth", until I started reading that nonsense. Was under the impression that you were just trying to troll first.

Thank you for your feedback. I updated my comment to make it clear that it was ChatGPT replying to my question.

The chatgpt output comes in chunks from openai's servers themselves, it can't get computed instantly. There's no way for this plugin to do what you want it to do.

OpenAI could return it instantly if they wanted.

Maybe, maybe not, but that's not the point. The original comment was blaming the plugin, which is not fair.

For the 2400 baud dialup?

All one is interested in is if he/she has a job. Rest is just corporate BS which one has to go along with.

I think people will work longer hours. This story has been played before.

Thanks. I'll check it out. It looks interesting.

The Polymath by Waqas Ahmed https://amzn.to/3MROulH

Thank you. I will give it a look.

A terminal that makes you sign in? I think I'll stay away from this one.

It was suppose to be a medium of exchange, instead it became an object of speculation.

It was supposed to solve the problem of trust in third parties.

Satoshi made this absolutely clear when he released the software and final version of the whitepaper, and he mentions it twice in the whitepaper.

https://satoshi.nakamotoinstitute.org/posts/p2pfoundation/1/...

You're looking for Bitcoin Cash, the Bitcoin that continued being a medium of exchange.

And it might end up being the global reserve currency.

I wonder if the 500 page comment Buffett made was ever meant to be taken seriously. Maybe he just said for the sake of motivating students.

How come there is no objection to the word master in the scrum master?

The standups are beyond hopeless. Grossly inefficient way of getting an update every day. we have not learned anything.