{"id":36772,"date":"2022-09-22T16:57:45","date_gmt":"2022-09-22T14:57:45","guid":{"rendered":"https:\/\/www.skaylink.com\/?p=36772"},"modified":"2024-04-17T11:14:25","modified_gmt":"2024-04-17T09:14:25","slug":"how-ai-enhance-developers-productivity","status":"publish","type":"post","link":"https:\/\/www.skaylink.com\/en\/insights\/blog\/how-ai-enhance-developers-productivity\/","title":{"rendered":"How AI can enhance the developers productivity"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Home<\/a><\/span><\/span><\/p>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Blog<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t

How AI can enhance the developers productivity<\/h1>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tLearn how developers can use Copilot to increase their productivity.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSeptember 22, 2022\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\"Picture\n\t\t\t\t<\/div>\n\t\t\t\n\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\n\t\t\t\t\t\t\t Leonardo Benitez\t\t\t\t\t\t<\/span>\n\t\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

In the past years, we have seen many advances in Natural Language Processing: question answering, text generation, proofreading, etc. So, you should not be surprised about systems to assist developers, right?<\/p>\n

That\u2019s exactly what Github Copilot does, a tool from Microsoft that is advertised as \u201cyour AI pair programmer\u201d. At Skaylink GmbH we have been using it for a while, and now we\u2019ll share with you the main points of this productivity tool and how you can start using it too.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

First, how does it work?<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

It is powered by GPT-3, a large neural network that was trained with a huge amount of public internet texts (Wikipedia, blogs, StackOverflow, open repositories in Github, etc). There is nothing \u201cmagical\u201d about it: its architecture was described in detail in academic papers, its general architecture has been used for many years (including in NLP projects here at Skaylink), and since its debut many competitors have trained similar models. But even if not magical, GPT-3 achieves impressive results in many NLP tasks, and one could dare to say that it \u201cmemorized the whole internet\u201d.<\/p>\n

The strength of GPT-3 is text generation: you give it an initial text, and the network will return you the most probable text that could follow it. Quite generic, yeah? That\u2019s exactly the idea, and the \u201ctext\u201d can be anything:<\/p>\n

    \n
  • You give it \u201cwhat is the largest river by discharge volume of water in the world\u201d and it answers \u201camazon river\u201d<\/li>\n
  • You give it \u201cAngela Merkel was elected because…\u201d and it gives you 3 paragraphs of political analysis<\/li>\n
  • You give it \u201cint count = 20; for i in …\u201d and it completes a code that makes sense<\/li>\n<\/ul>\n

    Microsoft encapsulated that into a system that auto-completes code, and can be installed in many IDEs as a simple plugin. It shows some suggestions automatically while you type the code (which can be even just a comment), and you can accept the suggestion by pressing tab. If you press ctr+enter at any time, it will show 10 suggestions to continue your code. It usually completes from a few words to a few lines of code, but in some situations, it will generate 10 or 20 lines.<\/span><\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

    \n\t\t\t\t\t
    \n\t\t
    \n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t

    What it does well<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    Generates functional code:<\/strong>\u00a0its suggestions are mostly functional and make sense in the context of the code.<\/p>\n

    Followed my code style:<\/strong>\u00a0it named variables and guessed some string names in the same way as I was doing in my code, as well as correctly using functions and classes that I have just written.<\/p>\n

    Works for many libraries and APIs:<\/strong>\u00a0I initially thought that Copilot would shine only for \u201cgeneric\u201d code, pure logical problems. But no, and it even helped me with some very specific tasks (like AWS LaunchSpecifications JSON descriptions).<\/p>\n

    Works across files:<\/strong>\u00a0if I start writing a function in one file and then use this function in another file, copilot will autocomplete correctly.<\/p>\n

    Understand different languages:<\/strong>\u00a0both programming languages (python, javascript, etc) and natural languages (English, Spanish, etc). I was surprised when I wrote a comment in Portuguese and it autocompleted my comment in a way that made sense, almost like reading my thoughts, haha.<\/span><\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

    \n\t\t\t\t\t
    \n\t\t
    \n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t

    What it doesn\u2019t<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t\t\t\t\t

    GPT-3 is well known for having problems with\u00a0\u201clong term memory\u201d<\/strong>: it generates text where the phrases make sense among themselves, but the text as a whole is gibberish. So, you can expect Copilot to generate short pieces of code, but the architecture of the solution is still up to you.<\/p>\n

    Trash-in, trash-out:<\/strong>\u00a0if you don\u2019t provide enough context (like just opening a blank new file) or provide a confusing context (like having a lot of unrelated code together), the Copilot\u2019s result will be bad. It may be syntactically correct, but it won\u2019t perform anything meaningful. The developer is in control, and that won\u2019t change soon.<\/p>\n

    There are also open questions about how copilot behaves regarding\u00a0copyrights, licenses and privacy<\/strong>\u00a0matters. For instance:<\/p>\n

      \n
    • It was seen that sometimes it generated valid API keys<\/li>\n
    • It could have been trained with code that is available on the Internet, but under a license that requires citation or that requires your code to become open source as well<\/li>\n
    • It may use our own proprietary code to feed the system<\/li>\n<\/ul>\n

      Microsoft clarified all those points [at least partially] and there are extensive discussions in the community, but only with time we\u2019ll see how the system works as it becomes more and more popular.<\/p>\n

      While using it myself, the only moment I saw weird auto-completion was when copilot suggested the comment \u201cThis file is part of love-platform\u201d in a Lua file (l\u00f6ve is a game engine for the programming language Lua, and my program had no relationship with it). Also, Copilot recently added a new feature for \u201callow suggestions matching public code\u201d, with an also optional approval for \u201cAllow GitHub to use my code snippets for product improvements\u201d. Interesting… I don\u2019t completely understand my code will be used by Microsoft, but I trust that they are doing a serious work.<\/span><\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

      \n\t\t\t\t\t
      \n\t\t
      \n\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t

      How companies can use it<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t

      Copilot is available to individual developers and individual accounts within organizations (but organizations can\u2019t buy bulk licenses yet), and it costs \\$10 USD\/month or \\$100 USD\/year. After paying the subscription, you just have to install the plugin in your IDE (VS code, for example) and start coding. The plugin uses only the system\u2019s web API, so your computer doesn’t become slow because of it.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

      \n\t\t\t\t
      \n\t\t\t\t\t

      Alternatives<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
      \n\t\t\t\t
      \n\t\t\t\t\t\t\t\t\t

      One of the best known alternatives is Tabnine, whose pricing starts at \\$ 12 USD\/month per developer. The inference can run locally or on the cloud, and you can thwick small configurations like the length of suggestions and if the suggestions should be given for empty lines. Honestly, the code-completion quality was way bellow Copilot, and it requires more \u201csupervision\u201d: if I just go pressing tab (that is, accepting the suggestion) the generated code usually is pure giberish. Disclaimer: I have tested only the free version, and some peers told me that the paid version is considerably better. The paid version also have features that worth mentioning: train a model specific for your team\u2019s code, continuously improve the model from your code, github integration, among others.<\/p>\n

      There are also competitors that follow a different approaches for AI-assisted coding:<\/p>\n

        \n
      • Captain Stack brings answers from stack overflow (a famous online forum for development questions);<\/li>\n
      • OpenAI provides a code-competition REST API (they are the ones\u00a0actually<\/em>\u00a0fact behind copilot, not Microsoft, but I won\u2019t go into more details about this);<\/li>\n
      • Code Clippy provides a solution quite similar in functionality to Copilot, but completely free-and-open-source and using the cloud inference engine of HuggingFace (that is also widely used by the open-source community). I think that 100 dolar per year is an acceptable sum to pay for quality and trustworthiness of Microsoft\u2019s Copilot, so the Code Clippy model makes sense mostly for the companies that explicitly desire to support the open-source community.<\/li>\n<\/ul>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
        \n\t\t\t\t\t
        \n\t\t
        \n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t

        Conclusion<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
        \n\t\t\t\t
        \n\t\t\t\t\t\t\t\t\t

        I was impressed by Copilot, and it\u2019s usually not easy to impress me.<\/p>

        Besides being fun, it speeds up my coding process: I already know what I want to write, then I start writing it, Copilot completes parts of the code, I fix the wrong parts, and continue writing what I had in mind. The result is faster delivery and more confidence that I didn\u2019t make any silly mistakes.<\/p>

        It also induces me to write a more standardized and comprehensible code, since then the copilot recommendations are better in those cases. This sounds especially advantageous when you are learning something new, since then your code tends to be messier.<\/p>

        In summary, I can easily imagine Copilot and similar tools being widely used in a near future. Do you want to be at the cutting edge of AI-assisted development and productivity tools? We can provide you with the guidance and support needed, contact us and let\u2019s work together.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

        Learn how developers can use Copilot to increase their productivity.<\/p>\n","protected":false},"author":23,"featured_media":71781,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[26],"tags":[173,174],"class_list":["post-36772","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog","tag-development","tag-microsoft"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/posts\/36772","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/users\/23"}],"replies":[{"embeddable":true,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/comments?post=36772"}],"version-history":[{"count":7,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/posts\/36772\/revisions"}],"predecessor-version":[{"id":73614,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/posts\/36772\/revisions\/73614"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/media\/71781"}],"wp:attachment":[{"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/media?parent=36772"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/categories?post=36772"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.skaylink.com\/en\/wp-json\/wp\/v2\/tags?post=36772"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}