My experience with an AI coding tool today.
Me: Can you optimize this method.
AI: Okay, here's an optimized method.
Me seeing the AI completely removed a critical conditional check.
Me: Hey, you completely removed this check with variable xyz
Ai: oops you're right, here you go I fixed it.
It did this 3 times on 3 different optimization requests.
It was 0 for 3
Although there was some good suggestions in the suggestions once you get past the blatant first error
Don't mean to victim blame but i don't understand why you would use ChatGPT for hard problems like optimization. And i say this as a heavy ChatGPT/Copilot user.
From my observation, the angle of LLMs on code is linked to the linguistic / syntactic aspects, not to the technical effects of it.
Because I had some methods I thought were too complex and I wanted to see what it'd come up with?
In one case part of the method was checking if a value was within one of 4 ranges and it just dropped 2 of the ranges in the output.
I don't think that's asking too much of it.
I don’t think that’s asking too much of it.
Apparently it was :D i mean the confines of the tool are very limited, despite what the Devin.ai cult would like to believe.
That's been my experience with GPT - every answer Is a hallucination to some extent, so nearly every answer I receive is inaccurate in some ways. However, the same applies if I was asking a human colleague unfamiliar with a particular system to help me debug something - their answers will be quite inaccurate too, but I'm not expecting them to be accurate, just to have helpful suggestions of things to try.
I still prefer the human colleague in most situations, but if that's not possible or convenient GPT sometimes at least gets me on the right path.
My favorite is when I ask for something and it gets stuck in a loop, pasting the same comment over and over
Yeah it's wrong a lot but as a developer, damn it's useful. I use Gemini for asking questions and Copilot in my IDE personally, and it's really good at doing mundane text editing bullshit quickly and writing boilerplate, which is a massive time saver. Gemini has at least pointed me in the right direction with quite obscure issues or helped pinpoint the cause of hidden bugs many times. I treat it like an intelligent rubber duck rather than expecting it to just solve everything for me outright.
I tend to agree, but I've found that most LLMs are worse than I am with regex, and that's quite the achievement considering how bad I am with them.
Same here. It's good for writing your basic unit tests, and the explain feature is useful getting for getting your head wrapped around complex syntax, especially as bad as searching for useful documentation has gotten on Google and ddg.
That's a good way to use it. Like every technological evolution it comes with risks and downsides. But if you are aware of that and know how to use it, it can be a useful tool.
And as always, it only gets better over time. One day we will probably rely more heavily on such AI tools, so it's a good idea to adapt quickly.
You have no idea how many times I mentioned this observation from my own experience and people attacked me like I called their baby ugly
ChatGPT in its current form is good help, but nowhere ready to actually replace anyone
A lot of firms are trying to outsource their dev work overseas to communities of non-English speakers, and then handing the result off to a tiny support team.
ChatGPT lets the cheap low skill workers churn out miles of spaghetti code in short order, creating the illusion of efficiency for people who don't know (or care) what they're buying.
Yeap.... Another brilliant short term strategy to catch a few eager fools that won't last mid term
“Major new Technology still in Infancy Needs Improvements”
-- headline every fucking day
"Corporation using immature technology in productions because it's cool"
More news at eleven
unready technology that spews dangerous misinformation in the most convincing way possible is being massively promoted
ChatGPT and github copilot are great tools, but they're like a chainsaw: if you apply them incorrectly or become too casual and careless with them, they will kickback at you and fuck your day up.
Who would have thought that an artificial intelligence trained on human intelligence would be just as dumb
Hm. This is what I got.
I think about 90% of the screenshots we see of LLMs failing hilariously are doctored. Lemmy users really want to believe it's that bad through.
Edit:
I've had lots of great experiences with ChatGPT, and I've also had it hallucinate things.
I saw someone post an image of a simplified riddle, where ChatGPT tried to solve it as if it were the entire riddle, but it added extra restrictions and have a confusing response. I tried it for myself and got an even better answer.
Prompt (no prior context except saying I have a riddle for it):
A man and a goat are on one side of the river. They have a boat. How can they go across?
Response:
The man takes the goat across the river first, then he returns alone and takes the boat across again. Finally, he brings the goat's friend, Mr. Cabbage, across the river.
I wish I was witty enough to make this up.
I reproduced that one and so I believe that one is true.
I looked up the whole riddle and see how it got confused.
It happened on 3.5 but not 4.
Interesting! What did 4 say?
Evidently I didn't save the conversation but I went ahead and entered the exact prompt above into GPT-4. It responded with:
The man can take the goat across the river in the boat. After reaching the other side, he can leave the goat and return alone to the starting side if needed. This solution assumes the boat is capable of carrying at least the man and the goat at the same time. If there are no further constraints like a need to transport additional items or animals, this straightforward approach should work just fine!
I always thought of it as a tool to write boilerplate faster, so no surprises for me
Sure does, but even when wrong it still gives a good start. Meaning in writing less syntax.
Particularly for boring stuff.
Example: My boss is a fan of useMemo in react, not bothered about the overhead, so I just write a comment for the repetitive stuff like sorting easier to write
// Sort members by last name ascending
And then pressing return a few times. Plus with integration in to Visual Studio Professional it will learn from your other files so if you have coding standards it’s great for that.
Is it perfect? No. Does it same time and allow us to actually solve complex problems? Yes.
Agreed and i have the exact same approach. It's like having a colleague next to you who's not very good but who's super patient and always willing to help. It's like having a rubber duck on Adderall who has read all the documentation that exists.
It seems people are in such a hurry to reject this technology that they fall into the age old trap of forming completely unrealistic expectations then being disappointed when they don't pan out.
Exactly. I suspect many of the people that complain about its inadequacies don’t really work in an industry that can leverage the potential of this tool.
You’re spot on about the documentation aspect. I can install a package and rely on the LLM to know the methods and such and if it doesn’t, then I can spend some time to read it.
Also, I suck at regex but writing a comment about what the regex will do will make the LLM do it for me. Then I’ll test it.
Yes there are mistakes, but if you direct it to the right direction, it can give you correct answers
In my experience, if you have the necessary skills to point it at the right direction, you don't need to use it at the first place
it's just a convenience, not a magic wand. Sure relying on AI blindly and exclusively is a horrible idea (that lots of people peddle and quite a few suckers buy), but there's room for a supervised and careful use of AI, same as we started using google instead of manpages and (grudgingly, for the older of us) tolerated the addition of syntax highlighting and even some code completion to all but the most basic text editors.
AI is a tool, not a solution.
It does but when you input error logs it does pretty good job at finding issues. I tried it out first by making game of snake that plays itself. Took some prompting to get all features I wanted but in the end it worked great in no time. After that I decided to try to make distortion VST3 plugin similar to ZVEX Fuzz Factory guitar pedal. It took lot's of prompting to get out something that actually builds without error I was quickly able to fix those when I copied the error log to the prompt. After that I kept prompting it further eg. "great, now it works but Gate knob doesn't seem to do anything and knobs are not centered".
In the end I got perfectly functional distortion plugin. Haven't compared it to an actual pedal version yet. Not that AI will just replace us all but it can be truly powerful once you go beyond initial answer.
I just use it to get ideas about how to do something or ask it to write short functions for stuff i wouldnt know that well. I tried using it to create graphical ui for script but that was constant struggle to keep it on track. It managed to create something that kind of worked but it was like trying to hold 2 magnets of opposing polarity together and I had to constantly reset the conversation after it got "corrupted".
Its useful tool if you dont rely on it, use it correctly and dont trust it too much.
GPT-2 came out a little more than 5 years ago, it answered 0% of questions accurately and couldn't string a sentence together.
GPT-3 came out a little less than 4 years ago and was kind of a neat party trick, but I'm pretty sure answered ~0% of programming questions correctly.
GPT-4 came out a little less than 2 years ago and can answer 48% of programming questions accurately.
I'm not talking about mortality, or creativity, or good/bad for humanity, but if you don't see a trajectory here, I don't know what to tell you.
This is a most excellent place for technology news and articles.
