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

111–120 of 672 posts

Re: Copilot regurgitating Quake code, including sweary comments

#111

Post by danparsonson »

aj3 wrote: post #73
stefan_ wrote: post #6

Even includes the commented out code. Clearly Copilot has gained a deep understanding of code and is not simply the slowest way to make a terrible, opaque search engine ever!

Does GitHub Copilot write perfect code? No. GitHub Copilot tries to understand your intent and to generate the best code it can, but the code it suggests may not always work, or even make sense. While we are working hard to make GitHub Copilot better, code suggested by GitHub Copilot should be carefully tested, reviewed, and vetted, like any other code. As the developer, you are always in charge. https://copilot.gith…

> ...may not always work, or even make sense...

Naively, as someone who just heard of this - that sounds worse than useless. If you can't trust its output and have to verify every line it produces and that the combination of those lines does what you wanted, surely it's quicker just to write the code yourself?

Re: Copilot regurgitating Quake code, including sweary comments

#112

Post by School-Cotton »

ronnier wrote: post #104
gentleman11 wrote: post #94

Earlier quoted context omitted.

> 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?

In its base unit. So cents in USD. Which can be an int64 Or if your language has something specific built in, use that.

Not necessarily. It depends on the application.

Re: Copilot regurgitating Quake code, including sweary comments

#113

Post by lordgilman »

gentleman11 wrote: post #94
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?

Integer cents or an arbitrary precision decimal type.

Re: Copilot regurgitating Quake code, including sweary comments

#115

Post by Uehreka »

danuker wrote: post #7

They could train on solely MIT-licensed code, and dump ALL the copyright notices of code used for training into a file. Problem solved.

Plenty of people probably copy-paste GPL code with the comments and stick MIT on it. This kind of thing violates the GPL, but I’m pretty sure (IANAL) that such code is “fruit of the poison tree”, and if you then copy it, you too can be held responsible. Sure, you might not get caught, but it’s a rough situation if you do.

Re: Copilot regurgitating Quake code, including sweary comments

#116

Post by _ZeD_ »

gentleman11 wrote: post #94
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?

python has the `decimal` module in the stdlib

Re: Copilot regurgitating Quake code, including sweary comments

#117

Post by slver »

pydry wrote: post #106
slver wrote: post #87

Earlier quoted context omitted.

> 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…

It's true I probably wouldnt have laughed quite as loudly if there werent a chorus of smug economists telling us that tools like this are gonna put me out of a job.

Business types hate dealing with programmers, that's a fact. And these claims of "we'll replace programmers" happen with certain precise regularity.

Ruby on Rails was advertised as so simple, startup founders who can't program were making their entire products in it in a few days, with zero experience. As if.

Re: Copilot regurgitating Quake code, including sweary comments

#118

Post by tyingq »

gentleman11 wrote: post #94
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?

There's no one answer, but decimal counts of the smallest unit that needs to be measured is common. Like pennies in the US, or maybe "number of 1/10 pennies" if there's things like gasoline tax.

Re: Copilot regurgitating Quake code, including sweary comments

#120

Post by volta83 »

slver wrote: post #107
volta83 wrote: post #100

Earlier quoted context omitted.

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 la…

It's very easy: don't use copilot code verbatim, and you won't have GPL code verbatim.

> It's very easy: don't use copilot

Fixed that for you.

Verbatim isn't the problem / solution. If you take a GPL'ed library and rename all symbols and variables, the output is still a GPL'ed library.

Just seeing the output of GPL'ed code spitted by copilot and writing different code "inspired" by it can result in GPL'ed code. That's why "clean room"s exist.

Copilot is going to make for a very interesting to follow law case, because probably until somebody sues, and courts decide, nobody will have a definitive answer of whether it is safe to use or not.

Post reply on HN