Maybe it is
Isn't that basically how it works?
Just add an additional group of monkeys that aggressively hires and fires the others based on performance
Tada, machine learning
this post was submitted on 01 Oct 2023
587 points (97.9% liked)
Programmer Humor
32716 readers
305 users here now
Post funny things about programming here! (Or just rant about your favourite programming language.)
Rules:
- Posts must be relevant to programming, programmers, or computer science.
- No NSFW content.
- Jokes must be in good taste. No hate speech, bigotry, etc.
founded 5 years ago
MODERATORS
It was the best of times, it was the blurst of times!
asks for password hashing
gets code that looks like password hashing, named like password hashing, but, without any of the hashing
But it has better performance
hash-lite
but, without any of the hashing
Or it's something like unsalted MD4.
It generates the blurst of code!
I've been using copilot and find it's suggestions are perfectly cromulent.
I turn to copilot whenever I need to embiggen my code
Tbh, copilot was probably the worst AI coding experience I've had. It actually made me less productive and made me question my competency as a programmer at the same time. Straight up did not have a good time. Use Cody or GPT-4 instead.
It is designed for other purposes than GPT models. Next time try to use copilot as autocompletion, not to generate new code. It's excellent in that.
That's how I thought it was supposed to be used. It's "copilot" not "autopilot". I don't need nor want it to write whole functions for me.
Company ran a trial for it, and it worked really well for generating boilerplate code following our existing system design. Sometimes it makes mistakes, but during the trial it was a rare occurence
The company is giving it to us all for free next year, hope it doesn't negatively affect hiring though...
The company is giving it to us all for free next year, hope it doesn't negatively affect hiring though...
Should be fine. No way they'll assume that the new technology is magic and over promise, under budget, and then start a company death spiral, before cashing out their stock options and doing the same somewhere else. I'm sure glad we don't see that all the time in tech. /s
That's how I was using it; I ended up spending as much time as I was saving going around and cleaning up after it and/or second guessing myself. Basically, because it only operates in the context of the file you're working in, it will suggest garbage half the time if you have to work with resources from other files.
From the docs:
GitHub Copilot analyzes the context in the file you are editing, as well as related files
Tho, I don't know if it allways been that way, maybe they added bigger context later
If you have those other files open, it also picks those up. And lately it seems to follow imports too, I feel like
But the propaganda from GitHub said it was making devs 80%+/- more productive!
How could this have happened? /s
it works well for me, mostly accurately guesses what I am trying to do, helps a ton with boilerplate code
It was 55% for me. Higher baseline I suppose. <\s>
Because we are the apes that wrote the code that copilot read.
I’m not understanding the CoPilot hate. It’s an amazing tool if you are competent. Even when it gets it wrong it still saves me 90%+ of the typing then I just correct what it did differently than how I want it.
Boilerplate becomes a breeze and I work way better when I have something to iterate on rather than coming up with it from scratch. It lets me play with and test ideas way faster and sometimes even does it differently than I’d do it which leads to learning new things and/or looking at the problem in a different way. I don’t blindly follow its output, sometimes I reject it wholesale, sometimes I edit it, sometimes it’s literally exactly what I would have typed myself.