Don’t forget we moved!
https://brandmu.day/
Learning to Code - A Sprite Break
-
Regarding the spelling error…
Thank you guys for catching that!
I’ve gotten it to float left! Margin is still wonky but I’ll hammer at that and report back later.
Thank you guys all again for the help so far.
-
Misread the title of this thread as ‘Learning to Code - A Spite Break’ and it seemed 100% appropriate. I have definitely needed many a spite break while learning to code.
-
One thing I’ve found extremely useful has been ChatGPT, giving it prompts like, ‘ChatGPT, let me show you some of my code and tell me what I’m doing wrong’ the answers are usually spot on. It’s a pretty good resource. If anyone ever feels stuck or is getting started, I strongly recommend trying it, even if you should always take answers with a grain of salt and know it can be confidently wrong sometimes.
-
@Apos said in Learning to Code - A Sprite Break:
it can be confidently wrong sometimes
Great, now AI is coming for my job.
-
@Apos said in Learning to Code - A Sprite Break:
I strongly recommend trying it, even if you should always take answers with a grain of salt and know it can be confidently wrong sometimes.
It may be helpful at times, but not only is it confidently wrong, it is often wrong in very subtle ways that are not immediately obvious or easily tested. That’s the reason AI-generated answers were banned from coding questions on StackOverflow.
-
What I like ChatGPT for is learning new frameworks and tech. I treat it like someone who already knows how the thing works and ask it questions. As long as it’s stuff that is generally available in documentation I find that it does a great job of finding and regurgitating even if I got the terminology not completely right.
IDK if I’d use it to write code for me though. Have not tried.
-
@shit-piss-love said in Learning to Code - A Sprite Break:
IDK if I’d use it to write code for me though. Have not tried.
Wasn’t there something on/with/in/around/orbiting loosely GitHub doing this kind of thing?
-
@Pavel said in Learning to Code - A Sprite Break:
@shit-piss-love said in Learning to Code - A Sprite Break:
IDK if I’d use it to write code for me though. Have not tried.
Wasn’t there something on/with/in/around/orbiting loosely GitHub doing this kind of thing?
Yeah a while after M$ bought github people started noticing VSCode’s autopilot feature suggesting very detailed code segments, and there were claims that some people recognized snippets from their company’s private repos. tldr; M$ is using private repos to train their AI.
-
@catzilla If there’s one thing I think all coders have run into, it’s a missing/extra thing, and beating one’s head against the wall trying to figure out why the code isn’t working properly…
Then the hole you make in the wall after you find that damned thing… xD
-
@Faraday said in Learning to Code - A Sprite Break:
@Apos said in Learning to Code - A Sprite Break:
I strongly recommend trying it, even if you should always take answers with a grain of salt and know it can be confidently wrong sometimes.
It may be helpful at times, but not only is it confidently wrong, it is often wrong in very subtle ways that are not immediately obvious or easily tested. That’s the reason AI-generated answers were banned from coding questions on StackOverflow.
In all seriousness I would strongly recommend someone try ChatGPT first before going to search on StackOverflow. It’s just way faster and more likely to get a useful answer. There’s stuff I took forever searching that I was able to get a solid answer on in a few seconds going through AI, and the tone of StackOverflow tends to be intensely discouraging to people imo.
-
@Apos I’m not a big fan of the tone of SO either. I’m just reporting that the consensus among the programming community is that the answers coming out of ChatGPT are not good for any but the most basic software questions. Want to know how to do a for loop in Ruby or a bubble sort? Well-established, well-documented things? (because after all it’s just stealing the documentation from elsewhere) Sure, go for it. But for anything complicated? You’re just asking to be tripped up by an algorithm that thinks it knows what it’s doing but really doesn’t. Just my 2 cents.
-
@Faraday said in Learning to Code - A Sprite Break:
@Apos I’m not a big fan of the tone of SO either. I’m just reporting that the consensus among the programming community is that the answers coming out of ChatGPT are not good for any but the most basic software questions. Want to know how to do a for loop in Ruby or a bubble sort? Well-established, well-documented things? (because after all it’s just stealing the documentation from elsewhere) Sure, go for it. But for anything complicated? You’re just asking to be tripped up by an algorithm that thinks it knows what it’s doing but really doesn’t. Just my 2 cents.
Kind of a tangent, but for English Comp we are to do persuasive essays where the topic is relevant to the degree being pursued (mine is computer science). I chose overreliance on AI as my topic for exactly this (bolded) reason.
-
@Faraday I find SO is as likely as not to give you a 5 year old wrong answer. At work I tell people actively to avoid it.
-
@Polk Again, I’m not advocating in favor of SO. I’m just saying that even by the standards of a site that’s got its own set of issues, ChatGPT was generating such trash answers that it got banned.
-
This is an interesting thread assessing an AI-generated image of a lady in a kimono dress.
For my “knows next to nothing about kimonos” self, I look at it and say: “Oh, hey, yeah that looks pretty good.”
But as the kimono expert summarizes:
So you have a white-faced woman wrapped in fabric scrap with odd hair accessories & funeral undergarments; if I ran into her in Kyoto’s Gion at night I would probably freak out! The subtleness makes it almost nightmarish.
That’s basically how ChatGPT is with code (and a lot of other things). To the novice/uninitiated it may look good on the surface. But when you dig deeper, it’s just wrong on so many levels.
-
@Faraday I’m not a kimono expert or even novice but I can tell at a moderate glance that’s AI, too. The sleeves, and the way the folds don’t match above and below the belt. That’s the first thing I look at, making sure the borders of things make sense/line up. AI is not good at it.