AI can write code like humans, bugs and all

https://www.wired.com/story/ai-write-code-like-humans-bugs/

by mathematically • 5 years ago

30 55 5 years ago

wired.com

el_oni• 5 years ago

Well yeah it was trained on humans

Iv3• 5 years ago

Just like the first Go playing programs. Just you wait until it is trained by "self-play" against a compiler.

Skyy933• 5 years ago

The difference is that in Go you have a defined goal, its static. This is different from writing code or a novel. The goal is not only to write a book or a program, it has to be a entertaining book or a working code that solves MY problem but not any other problem.

AI currently does not understand language well enough, it recognises patterns but does not understand what its doing and why.

Jensson5• 5 years ago

And what kind of program would your AI write? Would it write a web-app? How would it figure out what the API should look like just based on self training against a compiler? Neither the compiler nor the AI code you mentioned have any understanding of web API's, there is no way it could code that.

AI isn't magic, it can't solve problems you don't give it. When doing alpha go they gave the AI all the rules for GO and told it to optimize for those rules. That works fine. But if you want it to make a web-app, what rules would you give it to optimise for? Do you have a web-app evaluator lying around somewhere we can use? If not I don't see it happening.

The current code helper solved that by telling the AI to solve the problem "write code that looks like this bunch of human written code". The AI can do that just fine, but code that looks like human written code isn't terribly useful since the AI doesn't understand what makes the code good, all it knows is that the code looks similar to what a human once wrote. This is cool, but as you can see this is very different from the real deal where the AI solves the real coding problem rather than "write something that looks like code" problem.

TheDudeMan• 5 years ago

Zero surprises here.

Skyy933• 5 years ago

Garbage in - garbage out. If training data are error-prone the AI learns the same errors. I think the most devs do not have to fear unemployment.

pama• 5 years ago

Is there anyone here with practical first hand experience that can comment about their impressions so far?

jameshiew2• 5 years ago

I've been using OpenAI Codex directly (so not Github Copilot) for some coding tasks and it's been useful enough that I am using it daily at this point, though mostly as like a sort of personal Stack Overflow, especially when working with unfamiliar APIs. Prompting it with a function signature/docstring of what you want to achieve can give a helpful and often functional example that uses that API, even if the code is not perfect.

It's also decent at doing tasks that would be easy for a beginner programmer but perhaps tedious. Like you can give it a function for generating random colors and a task like "expand the variable names in this function to be better", and it will change variable names like `r`, `g` and `b` to `red`, `green` and `blue`. Hardly amazing, and the latency of the API means it's not actually that useful in practice (yet), but with the right prompt it can do some impressive things, and I expect it to get much better in the near future. Pulling magic strings out of functions into constants and adding typehints to Python functions are other simple tasks I've found it OK for.

minimaxir2• 5 years ago

I stopped using GitHub Copilot. Not because of the accuracy of its predictions (or potential lack thereof), but because the cognitive overhead / distraction of getting inline suggestions made using Copilot not strictly a net positive in productivity.

And this is before GitHub will start charging for it.

fallat• 5 years ago

And you instantly realize the code which is being returned is almost always directly from a human being who wrote it anyway.

extheat• 5 years ago

Not true, it's very good at one-shot learning, even from code you've written in different languages.

minimaxir2• 5 years ago

FWIW the generations have been close to what had intended and/or follow the intended patterns, which appropriate variable names relative to the rest of the script.

But from a QA perspective close isn't enough.

jupp0r• 5 years ago

This is the future of Software Engineering: fixing AI's bugs.

vsareto• 5 years ago

At least the AI won’t be tempted to be clever with its code unless we tell it to

fridif5• 5 years ago

var cleverCode = bot.generateCodeFor(someCucumberTest, Mode.CLEVER)

Verdex• 5 years ago

I agree, but only because the AI won't be tempted. It will however write "clever" code all over the place.

https://www.damninteresting.com/on-the-origin-of-circuits/

Dr. Thompson peered inside his perfect offspring to gain insight into its methods, but what he found inside was baffling. The plucky chip was utilizing only thirty-seven of its one hundred logic gates, and most of them were arranged in a curious collection of feedback loops. Five individual logic cells were functionally disconnected from the rest — with no pathways that would allow them to influence the output — yet when the researcher disabled any one of them the chip lost its ability to discriminate the tones. Furthermore, the final program did not work reliably when it was loaded onto other FPGAs of the same type.

tacotacotaco• 5 years ago

I expect programmers' jobs will only be to write tests. If a bug is found another test is written and the AI will generate new code until the new test passes.

fridif5• 5 years ago

This will take approximately eternity for difficult problems, such as management changing their mind every day.

qsort• 5 years ago

Writing a test suite so comprehensive that the only programs that satisfy it are correct wrt the specification amounts to writing a formal proof, which is in most cases orders of magnitude harder and more time consuming than writing the code yourself.

Programming is ironically one of the worst use cases of AI, because often predictable failure is better than unexpected success.

"Fix the null pointer exception" is less expensive (time, money and mental energy) than "figure out why the code spits out garbage even though the test cases pass".

josefx2• 5 years ago

The future of AI will not be skynet, but priests of the adeptus mechanicus praying to the machine spirit and performing the rites in the hope that it will perform correctly.

endisneigh• 5 years ago

hot take: rather than AI, software development would be better served by just going into LTS maintenance mode. For each domain (web development, android, etc, css) pick a tool and everyone agrees that will be "the" tool for a decade or two.

this will reduce the amount of "possibilities" w.r.t. code by orders of magnitude and therefore make it easier to both read, write, and development tools to automate code.

of course this will necessarily reduce innovation, but at the expense of higher quality code, easier to maintain code and skills that are more transferrable.

falcor84• 5 years ago

A nice idea, but it's not a pareto equilibrium though; particularly not for developers.

lakis• 5 years ago

everyone agrees that will be "the" tool for a decade or two Sorry, I found this so funny. Immediately before that, everybody agrees that we will develop in the one and only true language. All other languages will be banished ;-) ;-)

fridif5• 5 years ago

With enough monkeys and typewriters, we don't need AI to go where we need to go.

hypertele-Xii• 5 years ago

Some of those monkeys will inevitably write AI though.

fridif5• 5 years ago

It's possible the monkeys might even write an AI that produces physical monkeys who then in turn produce AI!

d13• 5 years ago

AI is the monkeys

gvb• 5 years ago

AI writes code like a bad intern: pasting in "likely" blocks of code with no understanding of the intent. The difference is the AI pastes in "likely" blocks from github examples where bad interns paste from SO.

ctoth3• 5 years ago

Lots of people grumping about Copilot, has anyone actually used it? For a personal project writing a transpiler from an old language (LambdaMOO) to JS, I've actually found it quite helpful. I can write code like:

convertList(node: MooASTNode): List {

And then it just spits out:

    const entries: ASTNode[] = node.children.map((child) => {
      return this.convertNode(child);
    });
    return new List(entries, this.sourceLocation(node));
  }

This isn't exactly difficult to write or reason about, but it did save me quite a bit of time to just dash out the code that converts the parse tree to an intermediate tree in an hour or so and then just quickly look over and make a couple corrections.

It also helped making the ASTNodes, for instance:

export class If extends ASTNode {

resulted in:

  constructor(
    public condition: Compare,
    public then: ASTNode,
    public elseDo?: ASTNode,
    public override loc: SourceLocation | null = null
  ) {
    super();
    condition.parent = this;
    then.parent = this;
    if (elseDo) {
      elseDo.parent = this;
    }
  }

  @logCall
  toEstree() {
    return builders.ifStatement(
      this.condition.toEstree(),
      this.then.toEstree(),
      this.elseDo?.toEstree()
    );
  }

}

Again, this code is not gonna win any prizes, but it sure did save me a good chunk of time. Why so much hate for the tool?

Jensson5• 5 years ago

It is usually more work to verify that code is correct than to write correct code in the first place.

Edit: At least for me it isn't obvious at all that those snippets are correct.

ctoth3• 5 years ago

This is an abstract response to a concrete demonstration of usefulness. Of course, if I'm writing crypto code or something where I don't understand the domain well, relying on Copilot would be foolish. But for a well-defined problem like the one I faced, juggling tree representations and a little recursion, being able to specify what I wanted and have the machine generate the code was actively useful and did actively save time. Also, don't you read your code once you write it in the first place? IF you've written it, you know what you meant, and are more likely to read something you didn't even write there, whereas if you're checking over the shoulder of your computerized coworker who has no ego to get hurt, you can be as critical as you need to.

klyrs2• 5 years ago

Why so much hate for the tool?

Whose code did it copy and how is that code licensed?

ctoth3• 5 years ago

Since Codex sends your own surrounding code as context, I'm assuming, though have no way to check, that it picked up on the patterns from the other ASTNode classes. I somehow doubt someone wrote the precise same @logCall decorator and attached it to their toEstree methods on their own ASTNodes. This is one of the things I find valuable, you can give it lots of help just by deciding where you do the generation from, what code is in the context window. Also, if we're gonna start saying that simple conceptual things like AST processing are licensed, this is a scary world where very little new code will get written.

akomtu• 5 years ago

Another snake oil. Coding needs abstract thinking that only smartest of humans can do, while the AI crowd still can't replicate ant-level intelligence.

What would be an immense multiplier of software eng productivity is an intelligent auto-fixer tool: a compiler gives you an error, you know how to fix it, but it's a tedious work that wastes most of your time. Think of fixing build deps, rewriting method signatures to match the parent class, properly adding a library to your project. You'd write "include ssl.h; encrypt(message)" and the tool would add all the plumbing around it, in line with project guidelines.

spicybright• 5 years ago

Why does everyone assume developers won't read and edit the code generated to be more correct?

Analyzing, debugging, and fixing code is what we do all day.

It reminds me of people strongly against autocomplete for variable/function names.

tyingq• 5 years ago

Presumably, skilled developers won't be the majority working in roles where copy pasting from the AI tool is a common pattern. I like PHP, for example, but a fair amount of the criticism of existing PHP codebases is because the ecosystem attracts lower-skilled folks.

What you're mentioning will happen, some developers will use the tool the right way. I just don't think that will be the prevailing pattern.

codeenlightener• 5 years ago

AI can also read code like a human: https://denigma.app

Jensson5• 5 years ago

First code snippet I pasted in it got a conditional reversed so doesn't seem to be very reliable.

jameshiew2• 5 years ago

I haven't used Github Copilot but from what I understand it generates a completion from the text already in your file. Since OpenAI Codex can "understand" natural language instructions, I've found putting code into a prompt with extra context in natural language on what needs to be achieved can give decent results. e.g to generate a docstring, you might use a Markdown-ish prompt like

  # Writing a good docstring
  
  This is an example of writing a really good docstring that follows a best practice for the given language. Attention is paid to detailing things like 
  * parameter and return types (if applicable)
  * any errors that might be raised or returned, depending on the language
  
  I received the following code:
  
  ```{{{language}}}
  {{{snippet}}}
  ```
  
  The code with a really good docstring added is below:
  
  ```{{{language}}}

If you wanted a docstring in a particular format, you could add some specific examples as context to your prompt to get even better results.

jwommack• 5 years ago

We’ve been able to write buggy automated software for a very long time. That’s not interesting. It’s also not that interesting that stealing/replicating code replicates bugs.

When the AI/ML programs can actually create lines of code without references and do it with quality that’s when there’s a real story that isn’t playing tricks on tech authors for stock gains.

Tricks like this are why everyone always thinks big innovation is 5 years away when no one is really working on the things that’s make it 5 years away.

johnmorris100• 5 years ago

It is clear that technical progress is inevitable. I can show you an example of a site where almost all articles are written using AI (GPT-2, GPT-3). https://www.vproexpert.com/what-can-ai-do-today/ Is it badly written?

AI can write code like humans, bugs and all

Related Stories