{"id":33905,"date":"2023-11-13T11:57:26","date_gmt":"2023-11-13T19:57:26","guid":{"rendered":"https:\/\/insidebigdata.com\/?p=33905"},"modified":"2023-11-13T11:57:29","modified_gmt":"2023-11-13T19:57:29","slug":"ai-wont-eliminate-programming-but-can-make-it-better","status":"publish","type":"post","link":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/","title":{"rendered":"AI Won\u2019t Eliminate Programming, But Can Make It Better"},"content":{"rendered":"\n

Software programmers are looking over their shoulders these days, fretting about how quickly large language artificial intelligence models seem to be gaining on them and, specifically, whether those models threaten their jobs.<\/p>\n\n\n\n

Their fears are somewhat understandable. After all, ChatGPT, GitHub CoPilot, Google Codey, and a growing list of other models are available to help programmers write code. And a few companies may see AI models and programmers as interchangeable parts that can be easily swapped. But despite the anxiety, the number of programmers who will actually be replaced by AI is negligible.<\/p>\n\n\n\n

Programmers are still in high demand, even amid widespread layoffs affecting other jobs. In addition, the main benefit of AI models in programming has been as tools that assist programmers in building code. Neither of those two things are going to change anytime soon. What will change is how programming is done, with AI and programmers working together.<\/p>\n\n\n\n

Developers Still Have Plenty to Do<\/strong><\/p>\n\n\n\n

There is much more to a developer\u2019s workday than simply generating programming code. Meetings (whether productive or not), code reviews, testing, documentation, gathering (and understanding) requirements take roughly 80% of a developer\u2019s time; they only spend 20% of their time writing code. Bringing ChatGPT or another AI model into the picture won\u2019t eliminate that one-fifth of the job. Developers will have to write detailed prompts telling the AI what to do. They will have to test and debug the code generated by AI models, which frequently generate incorrect code<\/a>. Measured that way, if AI-generated code makes developers 50% more efficient in generating code \u2013 and that\u2019s probably optimistic \u2013 it still represents only a 10% increase in productivity overall.<\/p>\n\n\n\n

A 10% increase in productivity is significant, but even that savings will be eaten up by other tasks.  Security auditing will likely become more important, since programmers will have to work to understand the potential repercussions of code they didn’t write. Understanding \u201clegacy\u201d code to add new features also becomes more difficult: AI models still aren\u2019t very good at understanding how large software systems work. And AI models still aren\u2019t very good at high-level design and software architecture.<\/p>\n\n\n\n

This isn\u2019t to say that AI won\u2019t have benefits. Letting AI eliminate time spent looking up documentation and searching StackOverflow, or letting AI generate code and documentation even if it\u2019s only a rough draft, will allow developers to spend more time on design, testing, and other tasks that improve the quality of the final product.<\/p>\n\n\n\n

Making Developers More Efficient<\/strong><\/p>\n\n\n\n

While we\u2019ve all been impressed by the ability of tools like ChatGPT to generate good-looking code from a simple prompt, don\u2019t be fooled: if you\u2019re working on real-world software, you\u2019ll need detailed prompts that specify exactly what you want ChatGPT to do. You frequently have to tell ChatGPT how<\/em> you want it to do what you want it to do. What\u2019s the overall design, what\u2019s the stack, what external libraries and APIs to use: this is all information that the model needs, spelled out in full.<\/p>\n\n\n\n

Writing a detailed prompt is just a different way of programming\u2014giving thorough, comprehensive instructions on what you want a computer to do. It\u2019s programming at an even higher level, without the need for formalized syntax or semantics. This new kind of programming may be closer to the way human brains actually work. But human programmers are just as indispensable as they were before AI started to steal the spotlight.<\/p>\n\n\n\n

Meanwhile, developers can put the time they save into collaborating with users about their needs\u2014an important practice that has often been overlooked\u2014along with refining designs and ensuring security.<\/p>\n\n\n\n

Training for the Future<\/strong><\/p>\n\n\n\n

In venturing toward this new way of programming, developers will need to develop some new skills. For one thing, they will need to learn more about working face-to-face with customers to discover their needs and design software that best meets them. And they\u2019ll also need to learn more about the working of powerful but less than perfect AI tools.<\/p>\n\n\n\n

A recent <\/a>O\u2019Reilly report<\/a> on developer productivity found that the biggest challenges developers face with new tools are training, cited by 34% of survey respondents, and ease of use, named by 12%. That\u2019s a total of 46% of developers saying that new productivity tools come with a learning curve attached. As companies adopt AI tools to complement their developer teams, they should incorporate training and skills development into the process.<\/p>\n\n\n\n

AI Will Change Programming for the Better, With Developer Guidance<\/strong><\/p>\n\n\n\n

The scary stories about AI threatening programmers\u2019 jobs are overblown. Rather than supplanting the need for programming and eliminating jobs, AI is going to change how programming is done, and change it for the better.<\/p>\n\n\n\n

By taking over the job of writing the code\u2014guided by detailed prompts from the developer\u2014an AI can save developers up to 20% or so of their time, allowing them to spend more time on customer collaboration, design, security, and other steps to ensure quality software. They will be better able to respond to change and make improvements. Ultimately, developers\u2019 time, like the developers themselves, will become more valuable.<\/p>\n\n\n\n

It won\u2019t happen automatically, however. Like other new productivity tools, AI models have a learning curve. Training should be a part of plans to make the best use of what is a powerful new tool. AI models that are tested and properly incorporated into the programming pipeline will free developers to spend more time refining the product.<\/p>\n\n\n\n

With AI, developers aren\u2019t going to lose a job; they\u2019ll have a better job.<\/p>\n\n\n\n

About the Author<\/strong><\/p>\n\n\n

\n
\"\"<\/figure><\/div>\n\n\n

Mike Loukides is the vice president of emerging tech content at O\u2019Reilly Media<\/a>. He’s particularly interested in programming languages, Unix, AI, and system and network administration. Mike is the author of System Performance Tuning and a coauthor of Unix Power Tools and Ethics and Data Science. Most recently he’s been writing about data and artificial intelligence, ethics, and the future of programming.<\/em><\/p>\n\n\n\n

<\/p>\n\n\n\n

<\/p>\n\n\n\n

Sign up for the free insideBIGDATA newsletter<\/a>.<\/em><\/p>\n\n\n\n

Join us on Twitter: https:\/\/twitter.com\/InsideBigData1<\/a><\/em><\/p>\n\n\n\n

Join us on LinkedIn: https:\/\/www.linkedin.com\/company\/insidebigdata\/<\/a><\/em><\/p>\n\n\n\n

Join us on Facebook: https:\/\/www.facebook.com\/insideBIGDATANOW<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

In this contributed article, Mike Loukides, Vice President of Emerging Tech Content at O\u2019Reilly Media, makes the argument that the number of programmers who will be \u201creplaced by AI\u201d will be small and explains how the use of AI will change the discipline for the better.<\/p>\n","protected":false},"author":10531,"featured_media":33058,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"footnotes":""},"categories":[526,180,61,67,56,97,1],"tags":[1254,1350,1351,1245,1248],"acf":[],"yoast_head":"\nAI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA\" \/>\n<meta property=\"og:description\" content=\"In this contributed article, Mike Loukides, Vice President of Emerging Tech Content at O\u2019Reilly Media, makes the argument that the number of programmers who will be \u201creplaced by AI\u201d will be small and explains how the use of AI will change the discipline for the better.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/\" \/>\n<meta property=\"og:site_name\" content=\"insideBIGDATA\" \/>\n<meta property=\"article:publisher\" content=\"http:\/\/www.facebook.com\/insidebigdata\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-13T19:57:26+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-11-13T19:57:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_scientist_shutterstock_768047488_special.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1100\" \/>\n\t<meta property=\"og:image:height\" content=\"550\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Contributor\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@insideBigData\" \/>\n<meta name=\"twitter:site\" content=\"@insideBigData\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Contributor\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/\",\"url\":\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/\",\"name\":\"AI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA\",\"isPartOf\":{\"@id\":\"https:\/\/insidebigdata.com\/#website\"},\"datePublished\":\"2023-11-13T19:57:26+00:00\",\"dateModified\":\"2023-11-13T19:57:29+00:00\",\"author\":{\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/35a290930284d4cdbf002d457f3d5d87\"},\"breadcrumb\":{\"@id\":\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/insidebigdata.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI Won\u2019t Eliminate Programming, But Can Make It Better\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/insidebigdata.com\/#website\",\"url\":\"https:\/\/insidebigdata.com\/\",\"name\":\"insideBIGDATA\",\"description\":\"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/insidebigdata.com\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/35a290930284d4cdbf002d457f3d5d87\",\"name\":\"Contributor\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/36bffd267e38ed3f525205f67270e91b?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/36bffd267e38ed3f525205f67270e91b?s=96&d=mm&r=g\",\"caption\":\"Contributor\"},\"url\":\"https:\/\/insidebigdata.com\/author\/contributor\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/","og_locale":"en_US","og_type":"article","og_title":"AI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA","og_description":"In this contributed article, Mike Loukides, Vice President of Emerging Tech Content at O\u2019Reilly Media, makes the argument that the number of programmers who will be \u201creplaced by AI\u201d will be small and explains how the use of AI will change the discipline for the better.","og_url":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/","og_site_name":"insideBIGDATA","article_publisher":"http:\/\/www.facebook.com\/insidebigdata","article_published_time":"2023-11-13T19:57:26+00:00","article_modified_time":"2023-11-13T19:57:29+00:00","og_image":[{"width":1100,"height":550,"url":"https:\/\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_scientist_shutterstock_768047488_special.jpg","type":"image\/jpeg"}],"author":"Contributor","twitter_card":"summary_large_image","twitter_creator":"@insideBigData","twitter_site":"@insideBigData","twitter_misc":{"Written by":"Contributor","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/","url":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/","name":"AI Won\u2019t Eliminate Programming, But Can Make It Better - insideBIGDATA","isPartOf":{"@id":"https:\/\/insidebigdata.com\/#website"},"datePublished":"2023-11-13T19:57:26+00:00","dateModified":"2023-11-13T19:57:29+00:00","author":{"@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/35a290930284d4cdbf002d457f3d5d87"},"breadcrumb":{"@id":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/insidebigdata.com\/2023\/11\/13\/ai-wont-eliminate-programming-but-can-make-it-better\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/insidebigdata.com\/"},{"@type":"ListItem","position":2,"name":"AI Won\u2019t Eliminate Programming, But Can Make It Better"}]},{"@type":"WebSite","@id":"https:\/\/insidebigdata.com\/#website","url":"https:\/\/insidebigdata.com\/","name":"insideBIGDATA","description":"Your Source for AI, Data Science, Deep Learning & Machine Learning Strategies","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/insidebigdata.com\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/35a290930284d4cdbf002d457f3d5d87","name":"Contributor","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/insidebigdata.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/36bffd267e38ed3f525205f67270e91b?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/36bffd267e38ed3f525205f67270e91b?s=96&d=mm&r=g","caption":"Contributor"},"url":"https:\/\/insidebigdata.com\/author\/contributor\/"}]}},"jetpack_featured_media_url":"https:\/\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_scientist_shutterstock_768047488_special.jpg","jetpack_shortlink":"https:\/\/wp.me\/p9eA3j-8OR","jetpack-related-posts":[{"id":34200,"url":"https:\/\/insidebigdata.com\/2023\/12\/13\/delphina-raises-7-5-million-to-build-copilot-for-data-science\/","url_meta":{"origin":33905,"position":0},"title":"Delphina Raises $7.5 Million to Build Copilot for Data Science","date":"December 13, 2023","format":false,"excerpt":"Delphina, an LLM-powered copilot for data science, announced the closing of a $7.5 million seed round co-led by Costanoa Ventures and Radical Ventures with participation from 20+ prominent angel investors, including Stanford professor Fei-Fei Li. The funding will be used to expand its team and accelerate product development.","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_Science_shutterstock_1247255884_special.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":20233,"url":"https:\/\/insidebigdata.com\/2018\/04\/15\/dimensionalmechanics-launches-nml-2-0-pioneering-programming-language-ai-deep-learning\/","url_meta":{"origin":33905,"position":1},"title":"DimensionalMechanics\u2122 Launches NML 2.0: A Pioneering Programming Language for AI and Deep Learning","date":"April 15, 2018","format":false,"excerpt":"Despite the rising demand, most computer programmers and data scientists lack the specialized knowledge and tools required to build deep learning software solutions for their organizations. To address this, DimensionalMechanics\u2122, launched its next-gen NeoPulse\u2122 Framework 2.0, and an easy-to-use programming language, called NML 2.0, to make artificial intelligence (AI) more\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":34046,"url":"https:\/\/insidebigdata.com\/2023\/11\/30\/happy-birthday-chatgpt\/","url_meta":{"origin":33905,"position":2},"title":"Happy Birthday ChatGPT!","date":"November 30, 2023","format":false,"excerpt":"Today, November 30, 2023, mark\u2019s the first anniversary of OpenAI\u2019s ChatGPT. In the last year, the AI chatbot has secured support from major Silicon Valley companies and seen integration across various fields including academia, the arts, marketing, medicine, gaming, and government. These are exciting times, so we decided to put\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2023\/07\/ChatGPT_shutterstock_2249988847_special.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":33221,"url":"https:\/\/insidebigdata.com\/2023\/08\/28\/umass-amherst-computer-scientists-use-ai-to-accelerate-computing-speed-by-thousands-of-times\/","url_meta":{"origin":33905,"position":3},"title":"UMass Amherst Computer Scientists Use AI to Accelerate Computing Speed by Thousands of Times\u00a0\u00a0","date":"August 28, 2023","format":false,"excerpt":"A team of computer scientists at the University of Massachusetts Amherst, led by Emery Berger, recently unveiled a prize-winning Python profiler called Scalene. Programs written with Python are notoriously slow\u2014up to 60,000 times slower than code written in other programming languages\u2014and Scalene works to efficiently identify exactly where Python is\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_scientist_shutterstock_768047488_special.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":33588,"url":"https:\/\/insidebigdata.com\/2023\/10\/07\/microsofts-quest-for-the-next-killer-app\/","url_meta":{"origin":33905,"position":4},"title":"Microsoft\u2019s Quest for the Next Killer App","date":"October 7, 2023","format":false,"excerpt":"In this contributed article, Gordon McKenna, VP of Cloud Evangelist & Alliances at Ensono, discusses the situation with Microsoft strongly backing OpenAI, what can we expect the future to look like? Microsoft\u2019s investment into OpenAI was a clear move for the company to align itself with the next killer app\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/insidebigdata.com\/wp-content\/uploads\/2023\/08\/Data_scientist_shutterstock_768047488_special.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":18240,"url":"https:\/\/insidebigdata.com\/2017\/06\/30\/bonsai-expands-tensorflow-support-gears-extending-functionality-ai-platform-enterprises-building-industrial-applications\/","url_meta":{"origin":33905,"position":5},"title":"Bonsai Expands TensorFlow Support with Gears, Extending Functionality of AI Platform for Enterprises Building Industrial Applications","date":"June 30, 2017","format":false,"excerpt":"Bonsai, provider of an AI platform that empowers enterprises to build and deploy intelligent systems, released Gears, a top feature requested by customers in the Bonsai Early Access Program. Gears further extends the value of Bonsai to data scientists, providing them with a tool to manage, deploy and scale previously\u2026","rel":"","context":"In "AI Deep Learning"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/img.youtube.com\/vi\/6DGxiMnx2g8\/0.jpg?resize=350%2C200","width":350,"height":200},"classes":[]}],"_links":{"self":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/33905"}],"collection":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/users\/10531"}],"replies":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/comments?post=33905"}],"version-history":[{"count":0,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/posts\/33905\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/media\/33058"}],"wp:attachment":[{"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/media?parent=33905"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/categories?post=33905"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/insidebigdata.com\/wp-json\/wp\/v2\/tags?post=33905"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}