That’s why everyone switches jobs every few years.
Sure, the increased pay is nice, but the real benefit is not having to deal with the catastrophically awful code that you’re forced to write because product wants to ship this 3 months ago and you haven’t been given enough time to design and implement the system in a way that actually makes sense.
At this moment, I am staring at a 200-line block of postgresql that has about 40 JOIN clauses. It is not trivially or realistically debugable, testable, or extensible by anyone, including the people who wrote it (and no, I didn’t write this shitshow). There are basically zero nuanced tests around it, despite the fact that that’s a banner I’ve carried in a pretty militant fashion since starting at this place about 2.5 years ago, meaning that I trust this baroque confluence of relational db logic about as far as I can throw my car. It was done this way because “we’ll have time to go back and optimize it later (oh, sweet summer child)”.
Oh, I was fearing we worked together, so I just went to check one of my workplace’s megaviews. But no, it’s 448 lines.
I wrote its first version a few years ago, with less than 100 lines, then I rewrote it with common subqueries so it could be actually maintained. It was much larger by that point. Later I removed some of the ambiguous (and subtly bugged) subqueries and rewrite it to use only about half of them. Looks like I need to do something about it again.
My consolation is that I’m not the one maintaining it.
ChatGPT is banned by my employer, because they don’t want trade secrets being leaked, which IMO is fair enough. We work on ML stuff anyway.
Anyway, we have a junior engineer that has been caught using ChatGPT several times, whether it’s IT flagging its use, seeing a tab open in their browser during a demo, or simply just seeing code they obviously didn’t write in code I’m reviewing.
I recently tried to help them out on a project that uses React, and it is clear as day that this engineer cannot write code without ChatGPT. The library use is all over the place, they’ll just “invent” certain API’s, or they’ll use things that were deprecated/don’t work if you’ve even attempted to think about the problem. IMO, reliance on ChatGPT is much worse than how juniors used to be reliant on Stack Overflow to find answers to copy paste.
One of the dirty secrets at FAANG companies is that lots of people join from internships, and can get all the way to senior and above without ever needing to go through a standard, full technical loop. If you have a formal apprenticeship scheme, sometimes you’ll join through a non-tech loop.
The underlying problem is the same, it just became more accessible to copy code you don’t understand (you don’t even need to come up with a search query that leads you to some kind of answer, chatpgt will interpret your words and come up with something). Proper use of chatgpt can boost productivity, but people (both critics of chatgpt and people who don’t actually know how to code) misuse it, look at it as a “magic solution box” instead of a tool that can assist development and lead you to solutions.
Today we have chatbots. Yesterday we had search engines and stack overflow. Before that we had books. And before that? Well what do you know… software programming is a relatively novel field. It’s almost as if nobody has perfected how it should be learned.
The most valuable knowledge comes from experience. I copied plenty of code around during my learning days as well, and I still do it today. The most important part however is trying to understand the code you’re working with. If you can understand it, know when it fails, test it in the right way, etc., then sure, you could probably learn to code from chatbots. They provide the information, and you’re at liberty to do what you want with it. If you just copy it and forget, you’ll be a bad programmer. But it’s not like you couldn’t do that before either with the other sources that were available - there were plenty of bad programmers before we had these tools available too.
That said, there is a risk that these chatbots do not provide any useful context around the code that they produce. When you learned from a book or stack overflow, you were reading from a reasonably authoritative source that could explain the code that was produced. But the authority behind the code from chatbots is probably much weaker than what we have from stack overflow, which in turn was probably also weaker than what we have from books. Does it have an effect or learning? I have no clue. But I still think you can learn from chatbots if you use the output that they provide in the right way. (Disclaimer: I have never used one of them and have no experience with them.)
Basically, yeah. Dennis Ritchie wrote the C compiler because he knew exactly what her wanted to use it for and the kinds of code that he wanted to write. Then he went on to write the book that everyone used to learn the language.
This is true of probably every language, library, framework, etc. The original designer writes it because he knows what he wants to do with it and does so. Then everyone else follows. People then add more features and provide demonstrations of how to use them, and others copy them. It is extremely hard to just look at an API and use that to figure out exactly which calls should be made and in what order. Everyone just reads from the examples and adapts them as needed.
I strongly advise not to do that. As others pointed out, it really is just predicting the next word. It is worth learning about how to problem solve and to recognize that the only way to become a better program is with practice. It’s better to get programming advice from real people online and read the documentations for the functions and languages you are trying to use.
If the internet has succeeded in anything, it’s that the illusion of competence is worth more than the thing itself. Until someone calls you out, that is.
Just let me rewrite ONE report from scratch so it doesn’t check a specific unindexed table that it doesn’t actually need to check and causes the report to be killed by MSQL because it takes too long to run.
I’m still struggling with understanding for loops tbh. I kinda get them, but I can’t “make my own” so I don’t really understand them.
I’ve never had any schooling coding, just made some scripts with internet help when I switched to linux, and I have ADHD like fuck so I haven’t really tried to understand them in months, but yeah if anyone knows of a good website to help learn for loops and how to create them (when to use what variables and brackets and shit, etc) I’m taking recomendations.
Don’t let yourself down because you don’t know the syntax off the top of your head.
Even after 15 years of programming, and studying computer science, I would have to look up how to write loops, conditions, variable assignments in bash / sh / batch.
Coming to python from a primarily java focus background wasn’t any different. I knew what steps the program should do, but had to look up how to translate it into whatever language. And for further improvements what features the language has to express the things “in the style of the language”
Thanks, that encouragement is definitely helpful, it felt like I was struggling with something most programmers would consider should be mastered day 1, right after lunch because hello world is before lunch haha. Glad to know people still have to look it up even after a while sometimes.
Think about it though. When people say they want to “code AI” what they typically mean is they want to play with prompts and waste electricity on garbage models, not actually write any of the underlying models that power AI.
Well yes, but also people can use TenserFlow and other AI tools without learning how to properly code. And they can also get the results they want. So be afraid of the question “do you really need to know how to code” anymore.
If you want to disabuse yourself of the notion that AI is close to replacing programmers for anything but the most mundane and trivial tasks, try to have GPT 4 generate a novel implementation of moderate complexity and watch it import mystery libraries that do exactly what you want the code to do, but that don’t actually exist.
Yeah, you can do a lot without writing a single line of code. You can certainly interact with the models because others who can have already done the leg work. But someone still has to do it.
It really is big. From baby’s first prompting on big corpo model learning how tokens work, to setting up your own environment to run models locally (Because hey, not everyone knows how to use git), to soft prompting, to training your own weights.
Nobody is realistically writing fundamental models unless they work with Google or whatever though.
I've even heard people try and call slightly complex bots "AI" and claim they can code them (or their friend totally can lol). It's infuriating and hilarious at the same time.
If you’re doing something extremely skillfully, chat gpt will make the dumbest suggestions ever…
Chatgpt is good for learning ideas and new things as an aggregate of what everyone thinks about it. But as a coding tool it cannot reason properly and has rubber stamp solutions for everything.
I’ve got no issues with people using stackoverflow or chatGPT as a reference. The problem has always been when anyone just skims what they found and just paste it in without understanding it. Without looking at the rest of the comments, further discussion, or looking at any other search results for further insight and context.
I think chatGPT makes this sort of “carelessness” (as opposed to carefulness) even easier to do, as it appears to be responding with an answer to your exact question and not just something the search algorithm thinks is related.
programmer_humor
Active
This magazine is from a federated server and may be incomplete. Browse more on the original instance.