I have yet to watch people be THAT more productive using, say, Copilot. Outside of some annoying boilerplate that I did not have to write myself, I don't know what kind of code you are writing that makes it all so much easier. This gets worse if you are using less trendy languages.
No offense, but I have only seen people who barely coded before describe being "very productive" with AI. And, sure, if you dabble, these systems will spit out scripts and simpler code for you, making you feel empowered, but they are not anywhere near being helpful with a semi-complex codebase.
I’ve tried enough times to generate code with AI: any attempt to generate non absolutely trivial piece of code that I can do intoxicated and sleep deprived, is just junk. It takes more time and effort to correct the AI output as starting from 0.
- Generate extremely simple code patterns. You need a simple CRUD API? Yeah, it can do it.
- Generate solutions for established algorithms. Think of solutions for leetcode exercises.
So yeah, if that's your job as a developer, that was a massive productivity boost.
Playing with anything beyond that and I got varying degrees of failure. Some of which are productivity killers.
The worst is when I am trying to do something in a language/framework I am not familiar with, and AI generates plausibly sounding but horribly wrong bullshit. It sends me in some deadends that take me a while to figure out, and I would have been better just looking it up by myself.
Lol seriously there are deterministic commands I can run that give me correct and verified boilerplate to stand up APIs. Why would I trust some probabilistic analysis of all code found online (while dissipating ungodly amounts of energy and water) to do it instead?
When I heard people talk about writing specs in natural language, I want to ask them if they want fuzzy results too. Like 10x10=20 or having you account debited from x+e money where x is what you ask and e is any real number. Or having your smoke detector interpreting it’s sensor fuzzily too.
My point is that I don't think AI can meaningfully output code that would be useful beyond that, because that code is not available in its training data.
Whenever I see people going on about how AI made then super productive, the only thing I ask myself is "My brother in Christ, what the fuck are you even coding?"
I've definitely noticed Copilot making it less annoying to write code because I don't have to type as much. But I wonder if that significant reduction in subjective annoyance causes people to overestimate how much actual time they're saving.
No offense, but I have only seen people who barely coded before describe being "very productive" with AI. And, sure, if you dabble, these systems will spit out scripts and simpler code for you, making you feel empowered, but they are not anywhere near being helpful with a semi-complex codebase.