Comment by sky2224
13 hours ago
> Over the past six months I tried using Claude, chatgpt, Grok and Gemini. At best I got reminders of how things worked. People online say they use them to write their code. The code they supplied to me has NEVER worked or was so convoluted that I threw it away and did it myself.
I've been finding AI either works great for people or is just awful, and I'm having a hard time pinpointing where the problem is. I don't think there's a big intelligence gap between us, so it's not like others wouldn't be noticing the things you're claiming when using AI. I genuinely believe your experience has been bad, but the part I'm trying to figure out is why it's been bad.
So my questions are: have you given things a fair shot? Have you tried turning things on its side to see if approaching AI usage a different way results in significantly better and more useful results? Do you actually put thought into what you're writing in your prompts (i.e., if I took your prompt and gave it to a junior dev, would they know what to do)? Are you just using the free models available online or do you have a dedicated integration into your development environment through Github Copilot or other vendor(s)?
I mean what I'm about to say with zero offense, but this honestly reminds me of how the elderly generation says, "technology doesn't work for me because it's always broken", and when you go and try to coach them on how to use the technology that's problematic for them, it's as if you're casting black magic.
I don't think AI is the second coming of Christ or that we're anywhere near AGI, but I do believe it's an extremely useful tool that people should be using.
> So my questions are: have you given things a fair shot? Have you tried turning things on its side to see if approaching AI usage a different way results in significantly better and more useful results? Do you actually put thought into what you're writing in your prompts (i.e., if I took your prompt and gave it to a junior dev, would they know what to do)? Are you just using the free models available online or do you have a dedicated integration into your development environment through Github Copilot or other vendor(s)?
That any of this would be needed is a problem on the AI side, not the user side. It can't be expected that everyone puts in hours of upfront work, trying out models and different ways of working just to see if AI is there yet for them, every time a new SOTA model comes out. Time is limited.
Also, the more thought, time, and effort needs to be put into prompts, the less useful AI is.
> I took your prompt and gave it to a junior dev, would they know what to do?
While overall I'm getting decent enough results, the AI often makes mistakes that no human would make, like not styling or aligning a new button on a webpage the same as the buttons right next to it. In general, it has major trouble with having a coherent vision of the entire project.
It's also obedient to a fault, never pushes back on anything I suggest. I'm pretty sure if I asked for a low user value feature that nevertheless would have to increase backend complexity 10x, it would go ahead and just code it, no questions asked.
> I don't think AI is the second coming of Christ or that we're anywhere near AGI, but I do believe it's an extremely useful tool that people should be using.
Ah, same. Just remember, we're very early into LLMs, they're still very much a sharp tool for experts, not really safe or convenient to use for everyone (yet?).