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

Copilot regurgitating Quake code, including sweary comments

twitter.com

Post reply on HN
Print view View original

91–100 of 672 posts

Re: Copilot regurgitating Quake code, including sweary comments

#91

Post by serf »

onion2k wrote: post #45
mimixco wrote: post #16

Earlier quoted context omitted.

Awesome summary and thanks for trying it for the rest of us! Copilot sounded terrible in the press release. The idea that a computer is going to pick the right code for you (from comments, no less) is really just completely nuts. The belief that it could be better than human-picked code is really way off. You bring up a really important point. When you use a tool like Copilot (or copypasta of any kind), you are intro…

Stuff like Copilot makes programming worse and more difficult, not better and easier. Copilot makes programming worse and more difficult if you're aiming for a specific set of coding values and style that Copilot doesn't generate (yet?). If Copilot generates the sort of code that you would write, and it does for a lot of people, then it's definitely no worse (or better) than copying something from SO. The author of a…

>If Copilot generates the sort of code that you would write, and it does for a lot of people, then it's definitely no worse (or better) than copying something from SO.

Disagree.

Most SO copy-paste must be integrated into your project -- maybe it expects different inputs, maybe it expects or works with different variables -- whatever, it must be partially modified to work with the existing code-base that you're working with.

Copilot does the integration tasks for you. When one might have had to read through the code from SO to understand it enough to integrate it, the person using Copilot need not even invest that much understanding.

Because of these workflow differences, it seems to me as if Copilot enables an even more low-quality workflow than offered by copy-pasting from SO and patching together multiple code-styles and paradigms while hoping for the best; Copilot does that without even the wisdom that an SO user might have that 'this is a bad idea.'

Re: Copilot regurgitating Quake code, including sweary comments

#92

Post by GhostVII »

aj3 wrote: post #69
Anon1096 wrote: post #49

Earlier quoted context omitted.

Why would excluding GPL'd code be enough to not violate licenses? I don't understand why people think MIT or other licenses are free for alls to take code as they wish. The MIT license includes an attribution clause. And, as the linked video shows, Copilot is more than happy to take its code and put your pet license and copyright notice on instead. Isn't that equally as infringing as stealing GPL code? The idea of mi…

Copilot is a tool. If you take copilot's suggestions uncritically and push them to Github, - that's on you.

Sure but if you have to audit every suggestion to see if it violates copyright laws that's not a particularly useful tool.

Re: Copilot regurgitating Quake code, including sweary comments

#93

Post by vmception »

gpm wrote: post #86
vmception wrote: post #76

Earlier quoted context omitted.

Hm odd takes here. It's really weird for software engineers to judge something by its current state and not by its potential state. To me, it's clearly solvable by Copilot filtering the input code by that repository's license. It should only be certain open source licenses, maybe even user-choosable, or code-creators can optionally sublicense their code to Copilot in a very permissable way. Secondly, a way for the cr…

Practically every open source license requires attribution, if copilot has a licensing issue, training a model on only repositories with the same license won't fix it except for the extremely rare licenses which do not require attribution.

why not? it can just generate an attribution file or reminder

Re: Copilot regurgitating Quake code, including sweary comments

#94

Post by gentleman11 »

tyingq wrote: post #30

They have 4 hand picked examples on their homepage: https://copilot.github.com/ One has the issue with form encoding: https://news.ycombinator.com/item?id=27697884 The python example is using floats for currency, in an expense tracking context. The golang one uses a word ("value") for a field name that's been a reserved word since SQL-1999. It will work in popular open source SQL databases, but I believe it would bom…

> The python example is using floats for currency.

Dumb question, but what is the proper way to handle currency? Custom number objects? Strings for any number of decimal places?

Re: Copilot regurgitating Quake code, including sweary comments

#96

Post by gpm »

vmception wrote: post #93
gpm wrote: post #86

Earlier quoted context omitted.

Practically every open source license requires attribution, if copilot has a licensing issue, training a model on only repositories with the same license won't fix it except for the extremely rare licenses which do not require attribution.

why not? it can just generate an attribution file or reminder

Because it's an opaque neural network on the backend, it doesn't know if or from whom it copied code.

Re: Copilot regurgitating Quake code, including sweary comments

#97

Post by mkr-hn »

slver wrote: post #87
tyingq wrote: post #30

They have 4 hand picked examples on their homepage: https://copilot.github.com/ One has the issue with form encoding: https://news.ycombinator.com/item?id=27697884 The python example is using floats for currency, in an expense tracking context. The golang one uses a word ("value") for a field name that's been a reserved word since SQL-1999. It will work in popular open source SQL databases, but I believe it would bom…

> And these are the hand picked examples. This product seems like it needs some more thought. Everyone's self-preservation instincts kicking in to attack Copilot is kinda amusing to watch. Copilot is not supposed to produce excellent code. It's not even supposed to produce final code, period. It produces suggestions to speed you up, and it's on you to weed out stupid shit, which is INEVITABLE. As a side note, Excel a…

Have you met programmers? Even those who care about quality are often under a lot of pressure to produce. Things slip through. Before, it was verbatim copies from Stack Overflow. Now it'll be using Copilot code as-is.

Re: Copilot regurgitating Quake code, including sweary comments

#98

Post by konfusinomicon »

influx wrote: post #20

I get why marketing calls machine learning “AI”. I don’t get why engineers would think this is. Dumb.

it's the marketing magic bullet. each person shot is entranced by its promises, and given unlimited ammo to spread its lies. few possess armor capable of stopping them

Re: Copilot regurgitating Quake code, including sweary comments

#99

Post by louthy »

GlennS wrote: post #75
louthy wrote: post #5

This is utterly damning. I have already instructed my team that Copilot can never be used for our projects. Compromising the product because of unknowable license demands isn't acceptable in the professional world of software engineering. But if we put the licensing to one side for a moment... 1/ Everything I've seen it generate so far is 'imperative hell'. It is practically a 'boilerplate generator'. That might be u…

I'm inclined to agree with you, and actually I'm rather mistrustful of even basic autocomplete ever since a colleague caught me using it without even looking at the screen! But I wonder... Is this a difference of programmer culture? I think there are people who write successful computer programs for successful businesses without delving into the details. Without considering all the things that might go wrong. Without…

> What would they do with this?

Not get a job working for me ;)

More seriously, when I think back to when I was first learning programming - in the heady days of 1985 - I would often copy listings out of computing magazines, make a mistake whilst doing it, and then have no idea what was wrong. The only way was to check character by character. I didn't have the deeper understanding yet, and so I couldn't contribute to solving the problem in any real way.

If they're at that level as a programmer, to the point where their code is being written for them and they don't really understand it, then they're going to make some serious mistakes eventually.

If you want to step up as a dev, understanding is key. Programming is hard and gets harder as you step up and bite off bigger and more complex problems. If you're relying on the tools to write your code, then your job is one step away from being automated. That should be enough to light a fire under your ambition!

Re: Copilot regurgitating Quake code, including sweary comments

#100

Post by volta83 »

slver wrote: post #87
tyingq wrote: post #30

They have 4 hand picked examples on their homepage: https://copilot.github.com/ One has the issue with form encoding: https://news.ycombinator.com/item?id=27697884 The python example is using floats for currency, in an expense tracking context. The golang one uses a word ("value") for a field name that's been a reserved word since SQL-1999. It will work in popular open source SQL databases, but I believe it would bom…

> And these are the hand picked examples. This product seems like it needs some more thought. Everyone's self-preservation instincts kicking in to attack Copilot is kinda amusing to watch. Copilot is not supposed to produce excellent code. It's not even supposed to produce final code, period. It produces suggestions to speed you up, and it's on you to weed out stupid shit, which is INEVITABLE. As a side note, Excel a…

So how do you know if the code that Copilot regurgitates is almost a 1:1 verbatim copy of some GPL'ed code or not ?

Because if you don't realize this, you might be introducing GPL'ed code into your propiertary code base, and that might end up forcing you to distribute all of the other code in that code base as GPL'ed code as well.

Like, I get that Copilot is really cool, and that software engineers like to use the latest and bestest, but even if the code produced by Copilot is "functionally" correct, it might still be a catastrophic error to use it in your code base due to licenses.

This issue looks solvable. Train 2 copilots, one using only BSD-like licensed software, and one using also GPL'ed code, and let users choose, and/or warn when the snippet has been "heavily inspired" by GPL'ed code.

Or maybe just train an adversarial neural network to detect GPL'ed code, and use it to warn on snippets, or...

Post reply on HN