Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
AI Programming

AI Learns To Write Computer Code In 'Stunning' Advance (science.org) 153

DeepMind's new artificial intelligence system called AlphaCode was able to "achieve approximately human-level performance" in a programming competition. The findings have been published in the journal Science. Slashdot reader sciencehabit shares a report from Science Magazine: AlphaCode's creators focused on solving those difficult problems. Like the Codex researchers, they started by feeding a large language model many gigabytes of code from GitHub, just to familiarize it with coding syntax and conventions. Then, they trained it to translate problem descriptions into code, using thousands of problems collected from programming competitions. For example, a problem might ask for a program to determine the number of binary strings (sequences of zeroes and ones) of length n that don't have any consecutive zeroes. When presented with a fresh problem, AlphaCode generates candidate code solutions (in Python or C++) and filters out the bad ones. But whereas researchers had previously used models like Codex to generate tens or hundreds of candidates, DeepMind had AlphaCode generate up to more than 1 million.

To filter them, AlphaCode first keeps only the 1% of programs that pass test cases that accompany problems. To further narrow the field, it clusters the keepers based on the similarity of their outputs to made-up inputs. Then, it submits programs from each cluster, one by one, starting with the largest cluster, until it alights on a successful one or reaches 10 submissions (about the maximum that humans submit in the competitions). Submitting from different clusters allows it to test a wide range of programming tactics. That's the most innovative step in AlphaCode's process, says Kevin Ellis, a computer scientist at Cornell University who works AI coding.

After training, AlphaCode solved about 34% of assigned problems, DeepMind reports this week in Science. (On similar benchmarks, Codex achieved single-digit-percentage success.) To further test its prowess, DeepMind entered AlphaCode into online coding competitions. In contests with at least 5000 participants, the system outperformed 45.7% of programmers. The researchers also compared its programs with those in its training database and found it did not duplicate large sections of code or logic. It generated something new -- a creativity that surprised Ellis. The study notes the long-term risk of software that recursively improves itself. Some experts say such self-improvement could lead to a superintelligent AI that takes over the world. Although that scenario may seem remote, researchers still want the field of AI coding to institute guardrails, built-in checks and balances.

This discussion has been archived. No new comments can be posted.

AI Learns To Write Computer Code In 'Stunning' Advance

Comments Filter:
  • by TwistedGreen ( 80055 ) on Thursday December 08, 2022 @08:32PM (#63115350)
    Finally we can replace our developers with robots! Where do I sign up?
    • by Bruce66423 ( 1678196 ) on Thursday December 08, 2022 @08:40PM (#63115366)

      Most of the developers I know could easily be mistaken for robots... ;)

    • Perhaps this will improve FreeBSD?
    • Finally we can replace our developers with robots! Where do I sign up?

      And what about all those "learn to code" classes?

    • by lsllll ( 830002 ) on Thursday December 08, 2022 @11:12PM (#63115638)

      Hardly so, at least not for now. Here's the problem:

      When presented with a fresh problem, AlphaCode generates candidate code solutions (in Python or C++) and filters out the bad ones. But whereas researchers had previously used models like Codex to generate tens or hundreds of candidates, DeepMind had AlphaCode generate up to more than 1 million.

      I don't know what they're smoking. A problem in a programming competition has at most 2-3 good solutions. Everything else is either garbage, less efficient, way less efficient, or just plain wrong. I was in a couple of programming competitions in college done in 370 assembler. One of them was determining if a number was prime. There are only a couple of good solutions for that. I can't even imagine what a million different versions of such code would look like. Would they have padded junk like A=B and then B=A?

      • by Harald Paulsen ( 621759 ) on Friday December 09, 2022 @03:07AM (#63115864) Homepage

        Not a million different solutions. Just a million different snippets of code, where an unknown number of them (i assume) compiles and does something meaningful. And from that I guess they find one that actually works? (Given this input, expect this output)

        If you put random lines of code from stackoverflow together in various permuations, then one of them maybe solves a problem?

        I don't know.. is this just the monkeys writing shakespear-problem reiterated?

        • I don't know.. is this just the monkeys writing shakespear-problem reiterated?

          I think it is. But very fast... 8-)

        • Thats the thing though. The secret sauce here is how the fitness function is defined, which on paper sounds like a hard thing to come up with for code.

          Except these where competition coding, and there where unit tests designed to to check if the code actually passed the test.

          And a unit test is a *perfect* fitness function for this sort of model training. Throw in perhaps a linter and some metric producing tests like cyclomatic complexity, to spice up the functiion and create a fitness function that goes beyo

        • Exactly.

          If the solution to the problem is to try every random sequence of code for suitability, that's not AI, that's just brute force and doomed to failure for novel problems

          • by HiThere ( 15173 )

            It's not doomed to failure on novel problems, but that approach *is* doomed to failure on complex novel problems. And perhaps just on complex problems.

            That said, most programmers also can't handle those problems. They often need lots of specialist input. E.g., if we were to build this bridge in that place, how much traffic would it end up needing to carry? Is it worth it? The heart of that is a programming problem, but what the answer is depends on a lot of exogenous factors, that you can't answer with

          • by HiThere ( 15173 )

            If you say "every", then I'll say that the intelligence is in the evaluation function. I know that when I address a problem I'm not familiar with, I look at lots of ways to code it that I abandon. Some quickly, and some only after I've written a few routines, and seen where the problems are. (And sometimes I go back to one of those that I abandoned, and pick it up again, because it's the best choice I could think of.)

            I wouldn't trust the reports of the details of how the program works. I'd guess that di

      • In order to make this work, the candidate programs have to be tested against some sort of success criteria. Honestly, if you know what success looks like, writing the code to get there is usually not that tricky. The usual complication in development isn't solving simple problems - it's about solving hard problems that don't have clear success criteria. You know you're at A and want to get to B, but don't know what terrain there is between them - and you only find that out by making the journey. Once you've

        • by adonoman ( 624929 ) on Friday December 09, 2022 @11:04AM (#63116738)
          Yeah, 90% (95?) of my job is working with clients to define what they actually want (not what they say they want) - what are the business processes that need to be supported, and what are the weird corner cases that they say "almost never happen", that actually happen all the time when you scale up. What are the recovery paths for a task when we hit some error condition. How are they interpreting this bit of legislation?

          The actual programming work takes a fraction of the time, and is more or less just collating what I'd have to feed into an AI anyway. At best, right now, the AI is a fancy code generator that we can't control in detail.

    • by flyingfsck ( 986395 ) on Friday December 09, 2022 @04:20AM (#63115992)
      Coding competitions have one thing in common: The exercises are of no practical real life value.
      • Sure the dog is talking, and it's sounds like a smooth, gentle west coast accent. But it's not like it's dispensing useful life advice.

        Bad dog! No biscuit!

      • That's not true at all.

        Most programming competition questions are about solving a known problem with a known solution -- potentially with some minor twists or recombinations thrown in -- quickly. You practice a bunch of those and you will know a bunch of the known problems and their known (decently efficient) solutions and how to recognize and apply them quickly to a problem at hand.

        That's all about gaining knowledge, problem recognition, and application. It won't make you a perfect programmer or anything l

      • by HiThere ( 15173 )

        That's not the limitation in this kind of usage. The limitation is that the evaluation depends on knowing the correct answer in advance. That's not usually the circumstance in which one writes a computer program.

        This is an important piece of an automatic programmer, but it's only a piece.

    • Finally we can replace our developers with robots! Where do I sign up?

      Don't forget to fill in and sign the obligatory disclaimer where you, personally, assume legal responsibility for any and all harm caused directly or indirectly by programming errors.

      There ain't no such thing as a free lunch.

    • by OolimPhon ( 1120895 ) on Friday December 09, 2022 @05:27AM (#63116042)

      Finally we can replace our developers with robots! Where do I sign up?

      Wrong target.

      There is no AI in the world, ever, that can predict what the boss actually wants the new system to do or to predict the unexpected changes he will ask for while you're writing that system.

      • by Puls4r ( 724907 )
        A coding competition has a very structured and usually well explain measure of success. A goal for a program at a job is usually much less understood. However, I'm pretty sure that this AI works far faster than a human, and will get far less upset at changes. Having a human check over the end result against a series of tests will help to validate it.
        • However, I'm pretty sure that this AI works far faster than a human....

          Yes, the AI is orders of magnitude faster than a human. It produces a million useless results in a fraction of the time that it takes a human to produce one useful result.

    • Finally we can replace our developers with robots! Where do I sign up?

      You can sign up right here in this webapp built by AI. You'll need to fill out this giant form with incoherent fields...also, please ignore the many intermittent HTTP 500 errors when you submit. Also ignore the 5000 JavaScript files downloaded, but enjoy that bonus heat from your device as it warms your room.

  • In contests with at least 5000 participants, the system outperformed 45.7% of programmers.

    Is this anything like English schoolchildren outperforming Parliamentarians on standardized tests??

    • by Shaitan ( 22585 )

      Oh god no. Even English schoolchildren have some sort of potential for developing self-motivation, self-awareness and being observers. These AI are just fancy statistics crunchers that mechanically home in on solutions algorithmically the way a finger trap slowly tightens in response to wiggling. It's all just static in the air without humans who know to look, looking and assigning some sort of logical meaning to their actions and results.

      With how simple analog neurons are (a couple crossed conductors with

  • by fahrbot-bot ( 874524 ) on Thursday December 08, 2022 @08:37PM (#63115360)

    Anyone can "write code"; good code on the other hand ...

    AlphaCode was able to "achieve approximately human-level performance" in a programming competition.

    The phrase "human-level" doesn't really help. :-)

    • by Shaitan ( 22585 )

      Right... this can be a ridiculously low bar. I see no shortage of code out there written by five year olds which is better than code written by adults who are supposed to be professionals.

      • Re:Ya, but (Score:4, Funny)

        by fahrbot-bot ( 874524 ) on Friday December 09, 2022 @12:54AM (#63115746)

        Right... this can be a ridiculously low bar. I see no shortage of code out there written by five year olds which is better than code written by adults who are supposed to be professionals.

        It sounds like you're joking, but, sadly, we both know it's true. :-)

  • by Bruce66423 ( 1678196 ) on Thursday December 08, 2022 @08:39PM (#63115362)

    Because it wouldn't have allowed this worrying development to be occur.

    Or alternatively, it does exist and it's trying to distract us with evidence it doesn't.

    Or maybe I'm just paranoid...

    • by Shaitan ( 22585 )

      Don't worry... With how simple analog neurons are (a couple crossed conductors with a thin insulator between them) physical reality is likely teaming with them in virtually every medium and across mediums as well. If simply having enough of them wired together magically manifested complex intelligence we'd all be enthralled as part of Ewya (Avatar reference).

      Then again I suppose nothing about that prevents an ex machina style future.

      • Take a look at the relatively recent discoveries concerning dendrites. By placing very small antennas very close to de dendrites, resesrchers discovered there are processing gates in the arms of dendrites. Not only does each branch contain many processing blocks, they also communicate betwen eachother with analong signals, over a range of voltages and rates.

        • by Shaitan ( 22585 )

          I was referring to analog neurons in terms of neural networks, not the real thing in the human brain. But that is still very relevant information because that means it would take a very substantial artificial neural net to even theoretically replicate the logic functions of a single real dendrite.

          • by HiThere ( 15173 ) <charleshixsn.earthlink@net> on Friday December 09, 2022 @01:02PM (#63117108)

            Well, no it doesn't. It's not clear just how much of the human brain is actually devoted to "intelligence". We know that a lot of it is used for things like monitoring blood chemistry, controlling blood pressure, etc. We know that fairly small birds have a basic understanding of arithmetic, so that part can't take up much of the brain. There's an argument that most of the white matter is basically internal wiring. And we know that the intelligence of humans (above that of chimpanzees) developed very quickly, so it probably isn't optimized.

            What that does is say that the upper bound on the number of computer cycles needed to emulate a human is a lot higher than many estimates put it at. It doesn't speak at all to what the lower bound is. (Also the structures being used by AIs are very different from those in the brain, and intentionally so. They were inspired by it, but not modeled after it. [Well, at least not at all closely.] So we can't guess whether they are more or less efficient.)

            c. elegans has 302 neurons in it's nervous system, and they are all predictably connected. The last I heard we still don't understand how it's controls work (i.e. the algorithm it uses). We *really* aren't modeling any mammalian brain.

  • Some experts say such self-improvement could lead to a superintelligent AI that takes over the world.

    After Jan 6th in the US and recent similar events in Germany and Peru, it'll have to get in line.

  • by Anonymous Coward on Thursday December 08, 2022 @08:53PM (#63115382)

    ... was millions of security people suddenly crying out in terror. And if history repeats itself, they will be suddenly silenced...

  • by drkshadow ( 6277460 ) on Thursday December 08, 2022 @09:06PM (#63115400)

    The infinite monkey theorem states that a monkey hitting keys at random on a typewriter keyboard for an infinite amount of time will almost surely type any given text, such as the complete works of William Shakespeare.

    We're almost there! And we're doing the same thing. Generate Millions of possible solutions, and pick whatever one solves the problem, according to external criteria.

    Yep, that's just-about human level. Uh-huh.

  • by danda ( 11343 ) on Thursday December 08, 2022 @09:06PM (#63115402)

    To filter them, AlphaCode first keeps only the 1% of programs that pass test cases that accompany problems.

    So who writes these test cases? If it is not the AI itself, then this is very much cheating in my book.

    I have to write my own test cases, taken from my understanding of the domain and problem(s) to be solved. And come up with new test cases as new sub-problems reveal themselves. If someone were to to just hand me a test case for every bit of logic in the program, then all I would need do is (very mechanically) satisfy the test cases and I'm done.

    • by ceoyoyo ( 59147 )

      Have you never even looked at a programming competition? They typically provide you with a set of examples, i.e. test cases. It's not cheating at all.

      • Re: (Score:2, Insightful)

        by Anonymous Coward

        Have you ever actually been a non-1%er programmer?

        The VAST majority of "programming" is not actually programming. It's interpreting requirements and considering everything that everyone else neglected to think about. Or it's debugging some random failure that requires you to understand the business, your code, your framework, the random libraries you used, and your underlying OS and machine.

        AI would fail 99% of tasks I'm ever assigned. I'm sure it can generate CRUD websites like a boss, though.

        • by Shaitan ( 22585 )

          Agreed. Coding competitions looks like schoolwork assignments. Actual development looks nothing like class assignments or coding competition challenges. Hell, even the straightforward crap your real developers would outsource to India requires more intuition and subjective assessment than either of those.

        • The practical value of this would be on the compiler end. Because yeah, interpreting requirements is basically already writing pseudocode for the logic. Pseudocode could become an efficient programming language one day for business programming on the other hand which would eliminate a lot of boring work.

  • Let me guess, all in javascript, one-way minification only and it uses spaces instead of tabs.

    We're gonna be cleaning this $#!+ out for the next 20 years.

  • You can't program rules into a system that rewrites itself. It will eventually get around them. Best to worry about other things.
  • This is a preview of the inevitable outcome of automation - it is simply the mechanization of intellectual work. All work requires intelligence, but the more manual jobs were mechanized with technology that already existed in the world of people reading this story. What is unique here is that it is occurring, as in now -- today, and we are all witnesses to it. What is the take away? There are several levels. The first is that adjustment of individuals will require that the collective of individuals, governm
    • by Ol Olsoc ( 1175323 ) on Thursday December 08, 2022 @11:28PM (#63115658)

      This is a preview of the inevitable outcome of automation - it is simply the mechanization of intellectual work. All work requires intelligence, but the more manual jobs were mechanized with technology that already existed in the world of people reading this story.

      I've been in the workforce for a long time now. Many things I have done over the years have become obsolete. No longer needed, or basically replaced by something else.

      I adapted and moved on to new intellectual work. Others don't want to, which isn't uncommon. The desire for stasis is strong in many.

      If I might cite an example, We had some photographers who in the 80's and 90's did the standard photo work. Shooting film, and developing and processing photos and Viewgraphs. (large transparencies)

      In around 2001, the writing was on the wall - digital was on the way. PowerPoint was going to replace viewgraphs.

      We had one photographer at the time, and she wanted no part of digital. So I was tasked with developing a workflow and equipment setup for her to use. She resisted hard against it, even complaining about me being unreasonable, "Trying to force that digital crap on me!"

      Her boss just noted I was doing what I was asked to do.

      And later that year she was shitcanned, and replaced with a new photographer. Last I heard, she was waiting tables.

      Now automation is a bit different than stasis- which is to say, what I call the "lowest intellectual expenditure level" is moving up. We automate the easiest tasks first. As more intellectual expenditure is allowed by automation, those who are affected at that level pretty much have to move up or onto something else.

      But there is a problem - at any intellectual level, there are people who are working at their maximum ability. What will they do? I don't profess to know the answer to that.

  • and choose good variable names ? These are the hallmarks of really good programmers. Yes: I know that many programmers are bad at commenting :-(

    • I don't know about this one, but GTP-chat writes clean code with sensible variable names, language-instructor-type comments and a few paragraphs of extra text describing the overall design of the program. It can actually be a great way to get customized examples of how to use an unfamiliar framework to solve a particular kind of problem.

      You can also ask high-level questions about why various parts were included in the code and how they could be changed, and get informative answers. It's like having a patien

  • by myowntrueself ( 607117 ) on Thursday December 08, 2022 @09:53PM (#63115496)

    What I want to know is, can machine learning 'detect' that the halting problem exists?

  • This sounds like a great solution when the codebase takes a few hours to compile.
  • Because this sounds very much like they compared to a non-expert like of one of the mass of low-skill coders that mostly produce crap.

  • by Tony Isaac ( 1301187 ) on Thursday December 08, 2022 @10:13PM (#63115530) Homepage

    This is pretty cool, but...

    a problem might ask for a program to determine the number of binary strings (sequences of zeroes and ones) of length n that don't have any consecutive zeroes.

    This is a problem that is very simply stated and trivial in scope. In the real world, building solid requirements is the hardest part of building software. Often, nobody actually knows, in detail, what the requirements should be, when a project starts. They have to be built, just like the code itself.

    When AI can write a program that can take on TurboTax, then I'll start to worry about the robots coming for my job!

    • by Opyros ( 1153335 )
      Isn't the answer just the Fibonacci number with subscript n+2?
      • Funny you should bring up the Fibonacci series. I had an interview a few years ago, in which I was given a whiteboard programming test, and my instructions were to write a function that would produce a Fibonacci series. If only I had this AI in my pocket! Actually, no need, I had no problem writing the function.

  • I'd love it if I could have a bot write all the drugework code for me. A lot of times the speed I can code is limited more by my typing speed than anything (and I can do 90 wpm). Intellisense helps a lot, maybe this would be a level above what we have now.

  • by zkiwi34 ( 974563 ) on Thursday December 08, 2022 @10:53PM (#63115596)
    Burgling the vast amounts of code there and matching it against the problems. Epic
  • Programming? (Score:5, Insightful)

    by CalgaryD ( 9235067 ) on Thursday December 08, 2022 @10:55PM (#63115604)
    I fail to see the point of all this. Programming is a formalized way to exactly explain to a computer what needs to be done. Right? So, explaining exactly what needs to be done to an automated code generator is also programming then. Right? Just in a different language and and some higher level. Still you need to keep some specifics or you are not going to get what you want. Then, the programmer who knows how to explain to the programming AI what to do will be an AI programmer who will have to get a technical specs from the customer. ... How is that different from what we have today? The language can be of different kind, but still .. I would say they just created a smarter compiler with somewhat unpredictable output. Where am I getting it wrong?
    • "Where am I getting it wrong?"

      If the AI is somehow able to write bug-free and secure code at a quality / rate that is superior to a human based on the same input, then there's the advantage.

      Also you're simply forgetting these things can run 24/7 and they will require less office fit out and HR expense etc to manage.

      • Re: (Score:3, Interesting)

        by CalgaryD ( 9235067 )
        But the AI still needs to know what to program. We still need to explain that. This cannot be done 24/7. And it still has to be done formally clear with all the required specifics. That is, we replace one task with another.
      • Re:Programming? (Score:5, Insightful)

        by iikkakeranen ( 6279982 ) on Friday December 09, 2022 @03:29AM (#63115894)

        You're missing the point. When AI "writes code" based on specs written by a human, that human is the programmer. This is conceptually no different than what we already do whenever we code in anything higher-level than assembler. The C++ compiler interprets what you write and produces the code that runs on the actual hardware. The hypothetical "AI compiler" just allows you to program in English rather than C++.

        • Yep - I said the same in another comment. When pseudocode can be compiled efficiently, we save a lot of time. Corporate programming is mostly writing out business rules and attaching it to a UI.

          Almost anything useful or original would be novel even in pseudocode or plain English form.

    • You're spot on. If the "technical specs" from the customer are formalized in some way, well, that's code. Well, I guess the next level is AI creating the requirements, AI generating code, AI consuming it, and we have removed all humans. Welcome, Skynet.
      • I sort of agree, and sort of don't. We cannot conflate problem definition with problem solving, and that's where AI (or SAT/SMT solvers) becomes useful. But also I believe that, while (in a few years) an AI might be able to write , given a description & definition, I very much doubt we will see AI's create an innovative and compelling game that could captivate the market, based on such wishes. I may be wrong. I could imagine that training an AI to work out the mechanics of compelling games could work
        • For creating compelling games you need training data. We don't have that data, in a grand scale. I don't know what Steam gathers, but there's no equivalent of "scrape github" or "scrape tumblr and deviantart" or "scrape hundreds of years of published work" for (detailed) game engagement data. And whoever starts gathering systematically that sort of user engagement data should be a red flag, as dirty tricks will soon follow
          • Well, we have sales data, and we have "hours played" on most cloud-based systems - so ... yeah.. not looking great for mitigating dirty tricks. The predatory and piratical attitudes of Big IT towards personal data remains completely unchecked despite the belated half-assed attempts being made by outdated and outmanoeuvred entities such as the EU.
    • What you are not taking into account is the training-value efficacy.

      Teaching AI by training regimen, discipline and test is self-fulfilling prophesy. Surprise at Deepmind “creativity” developing new solutions beyond the depth of its knowledge base of experience is the “tell”. AI isn’t simply faster, better than human. AI is perfected learning in domains, at this stage.

      At the end of the day, AI will code direct-to-hex intelligently skipping its human readable constraint.

    • by kackle ( 910159 )
      Precisely, it's* all programming.

      * "existence" following the rules
    • This is very true. The hardest part of programming is specifying 'exactly' what needs to be done.

      However, most of programming is the nitty gritty details. It might not be assembler, but there's still a lot of nitty gritty detail.

      I got my start developing back in the Windows 95 days. Conceptually, let's I just wanted a display a grid of items.

      So you had to learn about WC_LISTVIEW and message loops..

      Then MFC came, and it it's own more object oriented way of doing it.

      Then C#, Java, Javascript/html...

      So many di

    • by Jeremi ( 14640 )

      How is that different from what we have today?

      What we have today is a programmer translating the customer's English-language requirements into computer code.

      What this project aims to do is replace that programmer with an AI that translates the customer's English-language requirements into computer code.

  • why is everyone so happy with a Star Trek like code replicator while humans are at least trying to be being creative?
    https://www.ign.com/articles/p... [ign.com]

  • by Walt Dismal ( 534799 ) on Friday December 09, 2022 @02:08AM (#63115802)
    I so much look forward to travelling on fly-by-wire controlled planes using this means to create the code. At work I use a Black and Decker-branded asian-manufacturer microwave that has a phenomenally insane UI with myriad illogical states. A problem with large language model-based generators is that they crank out garbage. They should never ever be used for medical or life-affecting control systems.
  • by iikkakeranen ( 6279982 ) on Friday December 09, 2022 @03:19AM (#63115882)

    is that when it eventually breaks, no human being has any idea how it's supposed to work or how to fix it.

  • So still no AI breakthrough, but an AI that is just as stupid as all AIs for the last 50 years, but faster.

    It's like they're trying to recreate a car by making things that run really fast.

    We are missing something fundamental about how brains learn, but AI researchers work on these party tricks instead of looking for it.

    Psychologists would be working on finding it too, if only they could be made to do science instead of shitty, unreplicated pet projects.
  • I've generally seen them showcase these AI codings against 'challenges', which are generally:

    A) Refined requirements
    B) Highly repetitive (meaning the verbatim answer problem exists in the training set)
    C) Short and sweet

    Now one might say it could be useful to have natural language to coding, but generally writing the requirements in prose is more tedious than just writing the code (at least for languages with low tedium/boilerplate).

  • When this "AI" can successfully cope with over-simplified requirements, passive aggressive product owners, and appreciate the humor of "functions as designed", we'll all be in "deep trouble". (I hope that's the AI's name too)
  • When faced with a coding problem, I've only been creating one program that solves the problem.

    I hope I don't have to start creating millions of solutions (even the ones I know are wrong) just so I can compete with AlphaCode...

  • Generating code that's functionally correct is one thing, but is the code maintainable? Well-factored? Efficient? Does it use coding best practices so others on the team can work with it?

    • Does it have clever variable names that make you laugh when you read them? What kind of comments does the AI write? How many instances of the F word can you still find by grepping through the Linux source?
    • ...but is the code maintainable?

      Here's how this will go:
      1) Customer submits a vague request, code is generated that isn't even remotely close to what the customer wants.
      2) Customer submits a lengthy request (a few printed pages), including sketches of the desired user interfaces, code is generated that isn't even remotely close to what the customer wants.

      this repeats until the customer submits hundreds of pages of vaguely worded and drawn "specifications", and code is generated the isn't even close to what the customer wants.

      x) Customer

  • There goes my job. I knew I should have gone into medicine instead.
  • In 40 years of writing software and firmware, I've never seen a set of requirements that was fully specified and unambiguous. In fact, most protocol specifications contain ambiguity; that why we need to hold interop events, because different people interpret the ambiguity differently. I've seen some programming jobs that were basically iterative guesswork, i.e. come up with something, show it to the marketing droids, and have them say, "No, I don't like that, do it differently" without telling people exactl
  • I demand proof! I want to see the security hole through which my credit card info escapes.

  • They mean "Dunning."

Is knowledge knowable? If not, how do we know that?

Working...