zibzob

I think it's a lot harder than it sounds. First, nobody can estimate time well enough to know how long something would have taken without AI. And then, it's comparing apples to oranges - there's the set of things people did using an AI agent, and the set of things they would have done if they hadn't used AI, and the two are just not directly comparable. The AI agent set would definitely have more lines of code, that's all I could really say. Maybe it would also contain a larger maintenance burden, lower useful knowledge in humans, projects that didn't need to be done or could have been done in a smarter way, etc.

It's not possible to tell if you're 10x faster, or even faster at all, over any non-trivial amount of time. When not using a coding agent, you make different decisions and get the task done differently, at a different level of architecture, with a different understanding of the code.

For everyone complaining about the issues with app shortcuts when using Dvorak, the solution is to use a keymap that switches to QWERTY when you hold down the CTRL or CMD key. It is a bit unfortunate that common CLI commands (`ls` is the worst offender) and semicolon usage in programming languages are designed around QWERTY, but I still prefer Dvorak.

This looks pretty cool, but from the page I can't tell if there's any interactivity supported...there's a button example but it seems to have no click handler?

Okay, from the examples there's something like this:

   if (isMouseDown && !scrollbarData.mouseDown && Clay_PointerOver(Clay_GetElementId(CLAY_STRING("ScrollBar")))) {

Okay, I see what you mean now.

Why were lamplighters better off in the long run, is "lamplighter" a term that means more than just somebody who goes around lighting the streetlamps at night? Honestly that seems like a pretty decent job even today, if we still needed it to be done.

They have no leverage against Apple, so I'm not sure what options they have. They can drop off the service and lose all revenue, while affecting no positive change. Other struggling developers will just take their place.

I might be missing your point, but I'm not sure abolishing copyright would make much of a difference, in terms of increasing the number of people who can professionally make media. Supply and demand doesn't work properly in mass media, because one movie can supply the demand of everybody in the entire world, pretty much. We don't need a singer in every town, we only need a handful of talented people who can supply the music demands for everybody in the world - it doesn't really matter who they are. I'm exaggerating a bit, but that's how I generally feel about it.

(Having said that, this article is pretty much "old man yells at cloud" for me.)

I like the message, but I feel like the article doesn't support the headline. Instead, it seems to be saying that you should make something that you are passionate about, and in return other people will want it. I have not found that to be true personally, although I would like for it to be true.

Post-mortem from after the stream today: https://devlogs.fun/projects/127-8bitbrain/log

That's true, but it works with smaller pieces of code already. You can paste a function into ChatGPT and it will attempt to explain how the code works. Maybe there are enough existing explanations of high-level concepts on the internet for it to work, if it just has the larger codebase in its training data as well. At this point I am wary of making predictions about what this type of AI is able to do. :)

Thanks for the links, I'll take a look at this and see if it's something I could reasonably achieve.

I see, that's what I was worried about. It would be really helpful if it could answer high-level questions about a big confusing codebase, but maybe it's not just a matter of showing it the code and having it work.

That looks promising! But I think it only works on small snippets of code and doesn't have an overview of the whole codebase...still, maybe it's coming down the line as they improve it.

Yeah, and this is pretty useful for small bits of code, but what I want is a way to ask questions about large projects. It would be nice to ask something like "which classes are responsible for doing X", or "describe on a high level how Y works in this code". But I'm not sure if that is actually possible with the current technology.

Does anyone know if there's a way to use this technology to help understand a large codebase? I want a way to ask questions about how a big unfamiliar codebase works. It seems like ChatGPT isn't trained on open source code, so it can't answer questions there. When I asked it how something works in the Krita source, it just hallucinated some gibberish. But if there's a way to train this AI on a specific codebase, maybe it could be really useful. Or is that not possible with this type of AI?