Live data from Hacker News

AI learns to write its own code by stealing from other programs

newscientist.com

121–130 of 160 posts

Re: AI learns to write its own code by stealing from other programs

#121
post #45

“It could allow non-coders to simply describe an idea for a program and let the system build it” This is not a new thought. The problem with it, however, is that such a description would have to be very precise or else leave room for different interpretations which in turn could lead to very different programs being generated. In particular, as programmers know, it's often the edge cases that pose the main difficulty…

Doesn't TDD basically provide a spec? Write a test, then let the AI generate a program that passes the test. If the program is still buggy, you didn't write sufficient tests.

A few years ago I read a post by Bob Martin about how you can solve code kata problems by applying a sequence of 'transformations' to pass one test at a time. His method is very mechanical... so mechanical, in fact, that I think it may be possible to automate it.

So I started tinkering with the concept, and I've got a bit of a start on it here:

https://github.com/michaelmelanson/autocoder

What's there is very rudimentary. The main class is a good place to start.

Basically I'm building up a library of transformations that can describe solutions to kata problems (the 'word wrap' one currently). The next step is to create a search algorithm to derive an ordered sequence of transformations from that library to pass an ordered sequence of tests.

Re: AI learns to write its own code by stealing from other programs

#122
post #45

“It could allow non-coders to simply describe an idea for a program and let the system build it” This is not a new thought. The problem with it, however, is that such a description would have to be very precise or else leave room for different interpretations which in turn could lead to very different programs being generated. In particular, as programmers know, it's often the edge cases that pose the main difficulty…

Not only is it not a new thought, but it's been the holy grail of large software companies for at least 30 years. You'd be surprised at how much money has been spent researching this problem. And, for those just coming into software engineering, this isn't a good sign. I see a lot of software engineers that don't fear the risk of automation. But, because software development is such a huge cost center and so much is controlled by software developers, complete automation is one of the most sought after technologies.

I don't mean to spew hyperbole, because complete automation is likely very far off. But, I just wanted to point out the market forces behind this type of technology are gigantic.

Re: AI learns to write its own code by stealing from other programs

#123
post #45

“It could allow non-coders to simply describe an idea for a program and let the system build it” This is not a new thought. The problem with it, however, is that such a description would have to be very precise or else leave room for different interpretations which in turn could lead to very different programs being generated. In particular, as programmers know, it's often the edge cases that pose the main difficulty…

One of the things about human software engineers is that they can make assumptions based on what the system is for. For example you may say that "this system has to accept payments from counterparties" and they will intuitively know that they are dealing with people's money, and to be careful of situations like double billing and the like.

Re: AI learns to write its own code by stealing from other programs

#124
post #59

Earlier quoted context omitted.

I would argue that every year programmers ARE more efficient at their jobs with adoption of new tools, frameworks and methodologies. Yet there is still not enough good developers.

yes and each new tool or helpful framework reduces the total number of developers needed. Just because we have yet to meet the demand for developers, doesn't mean that that demand is not decreasing over time. software development is quite a young industry, so its growth can easily outpace the efficiency gains resulting in more developers, until it doesnt. Development as an industry will need to maintain stronger grow…

You start out with n amount of programmer time demanded from projects a b and c, given that you can do x with y number of programmer hours. So imagine that increased efficiency means you can now do 2x as much fantastic now you only need n/2 right!

Not so fast now that you can do more with less d, e, and f are worth doing and n+ are now demanded.

Basically simple economics says that decreasing price, the price for a given unit of work going down increases the demand for such. This is not realistically infinite however most of the world has a long way to go to catch up with the developed world and the developed world itself seems to have no end in sight as far as demand for automation and tech.

It would strongly look like until it doesn't is so far out on the time horizon that it is hard to predict anything at all on that scale.

Re: AI learns to write its own code by stealing from other programs

#125

At least when code monkeys copy-paste from Stack Overflow, there's a trace of common sense in the loop. Yes, it's possible to copy-paste your way to working software without having a clue. No, it's not a very good idea. How about if we shut these clowns down and use the money for research that has a chance of improving anything?

calm down, it's not coming for your job yet. soon, though.

Care to defend that seems kind of synonymous with actually AI which doesn't look like its coming soon.

Re: AI learns to write its own code by stealing from other programs

#126
post #87

Earlier quoted context omitted.

As a technical manager, this actually isn't that far from what happens with teams of engineers. The less precise I am in describing the requirements of a system, the less correct solution is produced. This isn't to say that my team is incompetent or mindless -- far from it, I find them to be some of the most talented engineers I've had the pleasure of working with. Perhaps the solution to this particular problem is a…

I'm not saying it applies to your case, but one danger of specifying a problem in too much detail, is that it teaches the engineers to think less about the problem. From my experience developers often think of failure cases that the managers are not aware of, or have a simpler solution to a problem.

This discussion reminds of this question/answer on quora: https://www.quora.com/Since-programming-can-be-self-taught-w...

Re: AI learns to write its own code by stealing from other programs

#127

In the meanwhile, Mark Cuban says: "I personally think there's going to be a greater demand in 10 years for liberal arts majors than for programming majors and maybe even engineering" (From this article: http://www.inc.com/betsy-mikel/mark-cuban-says-this-will-soo... )

I know he knows the business world and he obviously knows how to manage a business but what does he know about tech? This prediction is beyond nonsensical.

Re: AI learns to write its own code by stealing from other programs

#128
post #19

I thought this would take longer. "Developer" will stick around as a job for people who need new and unique things, or for apps that need speed, but if your job is making forms to take in data, putting it in a database, performing some sort of analysis on it, and then printing a report to the screen then you should really starting learning something else, because those jobs will not exist in 10 years.

Your timeline is hopelessly optimistic.

Re: AI learns to write its own code by stealing from other programs

#130

Earlier quoted context omitted.

> It is like vacation, forever. I guess that's one way to look at death from malnutrition, exposure or untreated illness. We can wax optimistic about what post-automation life could be like, but let's be honest: right now, unless you are an investor in companies that have automated or provide automation solutions, you are in absolutely no position to see 'vacation, forever' on the horizon for yourself or your childre…

Either we fix that, true, or there will be just far less people after a while. In the meantime, starvation may be a common "disease" in 1st world as well, just as it is already in the 3rd world. It's just that automation needs many people. It is to fix the problem of mass production. If there are no consumer masses, there is no need for mass production and thus no need for automation. But maybe the masses are just tu…

If people are starving in the street they will just tear down the nation around them on their way out sounds like a non survival strategy.
Post reply on HN