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

871–880 of 1001 posts

Re: GitHub Copilot

#871

Post by EGreg »

cbsks wrote: post #398

I don't think we need to start looking for new career paths yet. This example has a few bugs and it took me longer to track them down than it would have to write it myself: #!/bin/bash # List all python source files which are more than 1KB and contain the word "copilot". find . \ -name "*.py" \ -size +1000 \ -exec grep -n copilot {}\; "-exec grep -n copilot {}\;" needs to have a space before the semicolon otherwise f…

Give them a year. It sounds like the things people said about chess engines that played stupidly

Just kidding... writing imperative code is fundamentally different than most AI recognition tasks, ie you can have GPT-4 produce consistently nice HTML but not C++

Re: GitHub Copilot

#872

Post by thangalin »

cbsks wrote: post #798
nemetroid wrote: post #691

Earlier quoted context omitted.

It also doesn't list the files. It prints all matching lines (and their line numbers), without the corresponding filenames.

You are right! I missed that. The number of bugs to lines of code ratio is approaching one.

The following line is quite widespread in use, but not as portable as it could be:

    #!/bin/bash
For increased portability, respect users' PATH environment variable using:

    #!/usr/bin/env bash
Using #!/bin/bash could lead to subtle bugs on systems with more than one version of bash installed, or outright breakage on systems where bash isn't installed at /bin/bash. (OpenBSD is known to use /usr/local/bin/bash, for example.)

Re: GitHub Copilot

#873

Post by eloisius »

natfriedman wrote: post #143
jonas_kgomo wrote: post #93

Earlier quoted context omitted.

This is obviously controversial, since we are thinking about how this could displace a large portion of developers. How do you see Copilot being more augmentative than disruptive to the developer ecosystem? Also, how you see it different from regular code completion tools like tabnine.

We think that software development is entering its third wave of productivity change. The first was the creation of tools like compilers, debuggers, garbage collectors, and languages that made developers more productive. The second was open source where a global community of developers came together to build on each other's work. The third revolution will be the use of AI in coding. The problems we spend our days sol…

This innovation does not seem like a natural successor to compilers, debuggers and languages. If today's programming environments still require too much boilerplate and fiddling with tools, it seems like better programming languages, environments that require less setup, etc would be a better use of time. Using GPT to spit out code you may or may not understand seems more like a successor to WSDLs and UML code generators. I really hope we're just in a wild swing of the pendulum towards complex tooling and that we swing back to simplicity before too long.

Edit:

To expand a little and not sounds so completely negative towards AI, seems like there could be value in training models to predict whether a patch will be accepted, or whether it will cause a full build to fail.

Re: GitHub Copilot

#874

Post by TimTheTinker »

FunnyLookinHat wrote: post #493

This seems to work really well in cases where you're just laying down boilerplate. A few cherry-picked comments seem to suggest that React components are an ideal use case - which makes sense, that's a lot of munging and syntax to just render some strings. However, I find the process of writing these sorts of functions cathartic and part of the process to get into zen-mode for coding. I think I'd feel less joy in pro…

> However, I find the process of writing these sorts of functions cathartic

That may be true for individual contributors, but if you're trying to build a company from scratch, any help you can get to move faster is a good thing, cathartic or not.

Re: GitHub Copilot

#875

Post by stackbutterflow »

kif wrote: post #132
natfriedman wrote: post #60

Hi HN, we've been building GitHub Copilot together with the incredibly talented team at OpenAI for the last year, and we're so excited to be able to show it off today. Hundreds of developers are using it every day internally, and the most common reaction has been the head exploding emoji. If the technical preview goes well, we'll plan to scale this up as a paid product at some point in the future.

I visited https://copilot.github.com/ , and I don't know how to feel. Obviously it's a nice achievement, not gonna lie. But I have a feeling it will end up causing more work. e.g. the `averageRuntimeInSeconds` example, I had to spend a bit of time to see if it was actually correct. It has to be, since it's on the front page, but then I realized I'd need to spend time reviewing the AI's code. It's cool as a toy, but I…

Interesting comment and I agree. Reading and writing code seem to involve different parts of the brain. I wonder if tools like this will create some sort of code review fatigue. I can write code for a few hours a day and enjoy it but I couldn't do code review for hours, every day.

This isn't like skimming through a codebase to get a sense of what the code does. You'd have to thoroughly review each line to make sure it does what you want it to do, that there are no bugs. And even then, you'd feel left behind pretty quickly because your brain didn't create the paths to the solution to the problem you're trying to solve. It is like reading a solution to a problem on leetcode vs coming up with it yourself.

Re: GitHub Copilot

#876

Post by black3r »

anthropodie wrote: post #335
asdfman123 wrote: post #309

Earlier quoted context omitted.

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.

I kinda believe this but I still think it hugely depends on what you're doing in front of a computer. If you're just a generic developer that gets a task and codes it by the spec, then you can probably be replaced by AI in a few years.

But I don't think AI will become capable of complex thought in the next one/two decades, so if you're training to be a software architect, project manager, data analyst I think you should be safe for some time.

Re: GitHub Copilot

#877

Post by njharman »

qqqwerty wrote: post #451
anthropodie wrote: post #335

Earlier quoted context omitted.

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.

We went through the same hype cycle with self driving cars. We are now ~15 years out from the DARPA challenges and to date exactly 0 drivers have been replaced by AI. It is certainly impressive to see how much the GPT models have improved. But the devil is in the last 10%. If you can create an AI that writes perfectly functional python code, but that same AI does not know how to upgrade an EC2 instance when the appli…

15 years is no time at all.

Re: GitHub Copilot

#878

Post by rvz »

gervwyk wrote: post #703
visarga wrote: post #701

Earlier quoted context omitted.

far from it, this thing won't write full applications by itself

I know.. But we can dream. Also I'me sure when we first got code completion we said - "This thing won't write functions by itself."

The reality is the AI engineers that are working on AI autopilot systems for self-driving cars still tell their users to keep their eyes on the road. AI medical or doctor apps that suggest possible conditions still tell their patients to consult a real doctor. AI trading systems that auto-trade and analyse the markets are also limited and don't account for multiple risk points and still need supervision by the multiple traders and the lawyers using AI to sift through historical cases to save time still need supervision under a human lawyer.

Where we're going is assisted AI; obviously not a full on replacement as the scare stories created by the AI hype squad in this thread after the first reactions of this tool.

Re: GitHub Copilot

#879

Post by Nixinova »

FreeSpeech wrote: post #680
feross wrote: post #306

Earlier quoted context omitted.

I’ve also been using the Alpha for around two weeks. I'm impressed by how GitHub Copilot seems to know exactly what I want to type next. Sometimes it even suggests code I was about to look up, such as a snippet to pick a random hex color or completing an array with all the common image mime-types. Copilot is particularly helpful when working on React components where it makes eerily accurate predictions. I see techno…

Has anyone used Copilot with a more succinct language? It appears to only automate boilerplate and rudimentary patterns, which while useful in repetitive low signal to noise ratio languages like React or Java, sounds less appealing if you're writing Clojure.

Boilerplate is the most annoying type of code to write/try to remember, having all of that automated away would be awesome.

Re: GitHub Copilot

#880

Post by choward »

I don't understand what this has to do with pair programming. It's just a glorified auto complete for function bodies. You still have to come up with everything else. Filling in function bodies isn't what makes pair programming valuable.
Post reply on HN