124 likes
·
2.4K reads
8 comments
Super cool experiment!
let x = 34
Fascinating article, it’s cool that you’ve jumped on GPT-4 so quickly to test it out. I think speak for many developers that while this is exciting tech, it’s existentially threatening since it can potentially replace us. After having played with it, what is your prediction about AI replacing developers? Are you worried or excited?
Honestly, I'm both worried and excited. The excited part of me sees GPT-4 as a similar tool to Copilot where it can write concrete, well-defined blocks of code really easily, and that's actually great. Having it generate the CSS for a gradient background or build a simple modal saves me time and makes me as a developer more effective.
Today, I don't see it as something that can go build an entire real-world application with no direction. Even in this example, most blocks of code that it produced had at least one bug. And some of those bugs it just straight up couldn't fix.
The worried part of me assumes that it'll only get better with time. I'd guess that the most effective use of GPT-4 is going to be alongside a developer instead of a replacement for one, but who knows what future versions will bring.
PropelAuth nice answer! AI developers still need better middle managers for sure. So why don’t we focus on becoming one instead of worrying it’ll replace us haha
CrosswordGPT it is! I think this might be better than GitHub CoPilot.
Very cool, I tried a similar thing, where I asked it to invent a game like chess or checkers and then code it. My main frustration was that it would cut off its code in the answer in the middle, and wouldn't ever finish it no matter what I asked. I found ways to work around this, sort of, but have you experienced this and how did you deal with it?
Oh yeah, this is super frustrating and happens a lot. My go to fix was "Continue from 'return'" or "Continue from {the last line of code}"
GPT-4 would generally respond with "Here's the continuation..."
helpful PropelAuth