Somehow it feels different this time, the other technologies you mentioned were more niche and you could avoid talking about them. GPT is more pervasive. My Instagram feed was not full of microservices influencers at the time...

It's what happens when there are more people on the business of talking than doing

I'm waiting for new courses and ebook on how to become a gpt expert.

I’ve seen several of each advertised. (Well, “Generative AI” if not specifically “GPT” on the tin.)

I saw a course on GPT yesterday lol it has already started

I think GPT is still some ways off being as pervasive as blockchain nonsense was at its worst. Peak GPT Hype probably hasn't even arrived; celebrities aren't even being paid to sell you LLMs yet!

I realized only now that with this post I contributed to the GPT-chatter, sorry world!

It's substantially better.

I've compared the same prompts between both, and GPT-4 is always better, except when you need speed or it's a very simple task.

For complex tasks, especially requiring some sort or social understanding (I'm building a group AI sharing tool) it has a capacity for nuance which is sometimes surprisingly good. ChatGPT is usually more straightforward.

If anyone hasn't played with gpt4 yet I'm looking for testers on my platform and I have access.

Share it!

It’s far better at producing workable code, logical reasoning, keeping a train of thought, etc. Their benchmark breaks it down.

https://openai.com/research/gpt-4

It is much better, yes. The new 3.5 is still pretty good and very cheap, so it's my go-to for simple things, but GPT-4 is unmatched for complicated reasoning.

OP is referring to GPT4 API

How do you plan to keep this running for free?

We have some monetization ideas down the line, there's a lot of valuable goal-oriented information from the users.

In the meantime the cost per user per day is about a penny. We can slow down growth if it becomes too much.

Pretty cool. Do you plan on monetizing this somehow exposing an API or would you mind sharing the approach you took?

Curiously the example you mention is exactly what you get by using Linux with KDE and an Android phone using KDE Connect.

What are the differences compared to posthog?

Option B would be the most realistic and the one that makes most sense to me

You are still writing JSX in a string, aren't you?

No, you're not. There is no JSX of any sort in the example the parent commentor provided, nor in the approach that they present, even outside of that specific example.

The first parameter is the component, which is string containing the HTML tag name for built-in components which are basically just HTML elements, such as div, span, img, h1, etc, but the actual component (a function or a class) for any other type of component. The second parameter is the props. The third parameter is the children, which happens to be a string in this case because the content of the h1 in the example is pure text, but if you'd want anything more complicated as children, you couldn't put in a string and pass that, you'd provide it more React.createElement -provided values.

React at it's core is a function (or set of functions) that interpret strings like "h1" into DOM elements in a browser.

JSX is a shorthand for writing those function calls. <h1> becomes React.createElement("h1"). Sure you are still largely using HTML element names, but that's only because people don't really use JSX for anything else. The whole point is that it's easier to write JSX than the underlying function calls.

You can use JSX to target things other than DOM by supplying your own function instead of React.createElement(). Here's an example of an express web-server using JSX: https://betterprogramming.pub/how-to-create-a-web-server-wit...