Yeah, a lot of school bus stops on five lane highways… /s

My experience with LLMs for coding has been similar. You have to be extremely vigilant, because they can produce very good code but will also miss important things that will cause disasters. It makes you very paranoid with their output, which is probably how you should approach it and is honestly how you should approach any code that you’re writing or getting from somewhere else.

I can’t bring my self to actually use them for generating code like he does in this blog post though. That seems infuriating. I find them useful as a way to query knowledge about stuff that I’m interested in which I then cross reference with documentation and other sources to make sure I understand it.

Sometimes you’re dealing with a particular issue or problem that is very hard to Google for or look up. LLMs are a good starting point to get an understanding of it; even if that understanding could be flawed. I found that it usually points me in the right direction. Though the environmental and ethical implications of using these tools also bother me. Is making my discovery phase for a topic a little bit easier worth the cost of these things?

I feel like I’ve found a fairly sweet spot with LLMs and coding. I use them almost entirely like a rubber ducky. Any small bits of code that they do generate I then diligently try to understand, see inefficiencies or issues and come up with a better solution.

This is a pretty slow process so they don’t speed me up at all. They just make the initial discovery may be a little bit easier? As Google has gotten worse and especially if I’m working in a code base with limited documentation or bad documentation, I found them to be useful to get my bearings. I always go into it with a paranoia that anything they generate could be a disaster so I have to do extra due diligence.

I’ve found that they’re pretty good at generating a couple lines of code, though I have to usually refine it a lot. Anything more than that seems to be more trouble than it’s worth.

However, I have found them to be a great tool for learning even if I’m not sure if what they’re putting out is correct. It will usually lead me to start thinking about things and looking deeper into documentation and research papers, etc.

That there are so many ways to store data on a browser (including exploits) and that they expose so much information about your physical device is a big part of the problem. Even barring that, there are additional ways they can fingerprint a user. While any one thing might not be telling, when you take all of them in combination, it gets frighteningly accurate how easy it is for them to know exactly who you are.

I’ve heard it’s one of the best (if you’re looking for a full IDE experience). I haven’t tried it yet but I am on the lookout to hear about what tools people like to use for c/c++ development. Do you have one that you prefer?

The Odin Project has a whole section dedicated to only front end js. But that might be a bit of overkill but they will cover everything you requested.

If you’re mainly interested in how communication between the front end and the backend works using JavaScript, I would look into rest APIs and the browser’s fetch API specifically.

Ok that is good to know. As for qtcreator, it’s probably fine, just the first time I’ve used it and it didn’t have any of those features working correctly. And I already am familiar with jetbrains tools from Java development. I’ll just have to get it set up correctly. I know for sure I’ll be using it for its UI editing features.

The application is very resource heavy and is also designed for specific hardware, it can’t be run on the windows laptops we are provided. There are security concerns as well, which limit what I am allowed to do.

Currently I’m using vnc viewer to open a shell where I can run applications like qtcreator and get a gui interface. I’m sure I could run a local ide and ssh into the vm with it, but I know that can be tricky getting proper code coverage for jump to references to work. I guess I’ll try it and see what happens!

Interesting, I’ll probably still have to ask for permission to pull anything from the outside onto the vm, but hopefully will get less push back if it’s for a tool already installed and in use.

I’ve been using it via vnc, and was having a hard time with it. Perhaps I need to configure it correctly. Out of the box, jump to definition wasn’t working great and there doesn’t seem to be linting set up. Probably this is just me not knowing anything about c++ development and needing to do more research.

I think some people here are using vscode, I’ve not been a huge fan of it in the past but I should probably look into their workflow.