Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GitHub Copilot

copilot.github.com

Post reply on HN
Print view View original

331–340 of 1001 posts

Re: GitHub Copilot

#331

Post by YeGoblynQueenne »

pnt12 wrote: post #307
YeGoblynQueenne wrote: post #267

From the FAQ: https://copilot.github.com/#faqs >> How does GitHub Copilot work? >> OpenAI Codex was trained on publicly available source code and natural language, so it understands both programming and human languages. I want to propose a new Bingo style game where you get points when AI researchers (or rather their marketing teams) throw around big words that nobody understands, like, er "understands" with abandon.…

In AI research lingo "understands" really means "makes decent correlations".

Please provide a reference for this explanation.

Re: GitHub Copilot

#333

Post by booleandilemma »

sqs wrote: post #191

AI to write code is cool, but you know what’d be even cooler? AI for maintaining, upgrading, improving, and fixing code. After all, devs spend 80%+ of their time doing those things and they’re WAY more painful than writing code imo.

Please, replace me faster :)

Re: GitHub Copilot

#334

Post by mason55 »

cnvm wrote: post #245
tux1968 wrote: post #125

Earlier quoted context omitted.

How many jobs have developers helped displace in business and industry? I don't think it's controversial that we become fair game for that same automation process we've been leading.

Nothing is inevitable. Doctors and lawyers have protected their professions successfully for centuries. Only some software developers seem interested in replacing themselves in order to enrich their corporate masters (mains?) even further. Just don't use this tool!

This tool only replaces a small part of a good programmer and just further highlights the differences between people blindly writing code and people building actual systems.

The challenge in software development is understanding the real world processes and constraints and turning them into a design for a functional & resilient system that doesn't collapse as people add every little idea that pops into their head.

If the hard part was "typing in code" then programmers would have been replaced long ago. But most people can't even verbally explain what they do as a series of steps & decision points such that a coherent and robust process can be documented. Once you have that it's easy to turn into code.

Re: GitHub Copilot

#335

Post by anthropodie »

asdfman123 wrote: post #309
fzaninotto wrote: post #40

I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…

Pack it all up, boys, programming's over. Hello, AI. Anyone want to hire me to teach your grandma how to use the internet?

Few days back, Sam Altman tweeted this

"Prediction: AI will cause the price of work that can happen in front of a computer to decrease much faster than the price of work that happens in the physical world. This is the opposite of what most people (including me) expected, and will have strange effects"

And I was like yeah I gotta start preparing for next decade.

Re: GitHub Copilot

#336

Post by asdfman123 »

manquer wrote: post #198
theden wrote: post #88

Calling it now, there will be a "Copilot considered harmful" post. If you need to go through the suggested code to ensure it's correct, you may as well write it yourself? If you glance at it and it looks about right, you can potentially overlook bugs or edge cases, you'll lose confidence in your own code since you didn't properly conceptualise it yourself. Potentially for newer developers it robs them of active exper…

Think of it as a junior dev working under you and doing the grunt work of typing in your ideas. Sometimes he can StackOverflow a better snippet than you can write on your own, you will probably learn a bit from it, but it won't surprise you. It is no different from a code review of another perhaps junior dev and only doing adding finishing touches. There is plenty of boilerplate you have to write, Intellisense/ Auotf…

Most people on HN will probably be fine for a while. This innovation though, once properly developed, could completely screw over anyone wanting to enter programming.

Code completion might be the new "junior dev."

Re: GitHub Copilot

#338

Post by zild3d »

a-r-t wrote: post #246

One of the examples they provide on copilot.github.com shows a unit test for strip_suffix function. It does not test for a file name without a suffix, which the function would fail (it removes the last character instead): def strip_suffix(filename): """ Removes the suffix from a filename """ return filename[:filename.rfind('.')] import unittest def test_strip_suffix(): """ Tests for the strip_suffix function """ asse…

Great, you got 2 assertions for free, which lowers some friction of writing tests. You should still be thinking and be "the pilot". When you start writing additional test cases, it will help you out with those too

Re: GitHub Copilot

#339

Post by sktrdie »

jms55 wrote: post #208

So the AI doesn't actually understand the code does it? It only looks for similar things. So if I'm writing a game in Rust using the hecs ECS library, how is it going to help me? How many other people have written a game in that language using that library in this genre trying to do this task before? Probably very very few. And yeah that's a niche example, maybe this is super helpful for writing a react app or someth…

> how is it going to help me? How many other people have written a game in that language using that library in this genre trying to do this task before?

Because you write code using a bunch of patterns: iterating over data, destructing an object, calling functions etc. If you can generalize the usage of these patterns in such a way that it understands the context where you want to use them you're essentially doing this Copilot thing.

I agree that it'll be hard to have it understand fully the context and paradigms behind your existing project, but if it can help me automate some things in such a way that I can just let it run its thing and than have me "poke around it to get it right" then this is still amazing.

Re: GitHub Copilot

#340

Post by vincnetas »

ehsankia wrote: post #283
mdellavo wrote: post #193

Earlier quoted context omitted.

What do you think about this being overall detrimental to code quality as it allows people to just blindly accept completions without really understanding the generated code. Similar to copy-and-paste coding. The first example parse_expenses.py uses a float for currency - that seems to be a pretty big error that's being overlooked along with other minor issues around no error handling. I would say the quality of the…

How is it different from the status quo of people just doing the wrong thing or copy pasting bad code? Yes there's the whole discussion below about float currency values, but I could very well see the opposite happening too, where this thing recommends better code that the person would've written otherwise.

People make mistakes. With computers people make mistakes much faster :)
Post reply on HN