[sqeaky]

There's no it way won't suck, so it's good to github built in a way to iterate and called it experimental. We need much better llms, or some other technique, before we can have anything like this.

People have been trying this building software in plain English bullshit for at least 65 years, look into the history of cobol. It didn't work last time, or the time before, or the 50 times before that. It absolutely will work someday, but there's no compelling reason to believe that day is coming in the next month or two.

[bryanrasmussen]

>look into the history of cobol. It didn't work last time,

I believe that Cobol did work, in relatively narrow but important niches. It worked, but was hated.

[sqeaky]

Oh yeah Cobol absolutely worked as a programming language, but it never lived up to the promise of being a plain English replacement for code which was a common promise at the time.

[Szpadel]

of course, but to evaluate or train better LLM you need to have first some framework/application like gh spark working. just look at aider and how well it's able to estimate llm coding performance. like with everything in the past we need first to build something that is helpful for some cases and then improve it every generation.

I believe spark will be great for some internal tooling or some personal side projects, you don't have to handle every corner case in such application

[Bombthecat]

I think we don't really need better llm.

Biggest problem is the context window and understanding of context.

[sqeaky]

Those are features of the llm

[whazor]

Github Spark looks like v0.dev, and v0 is much faster than me in building a good UI in React. It also often creates better UIs than me. But after the basic interface is up, it’s better for me to connect it to the backend or add interactivity myself (with the help of inline copilot completions of course).

In the end, it does speed up my development of applications.