In the past year and a half, we have witnessed a technological leap that has fundamentally changed software development. Nowadays, it\u2019s enough to type it into a ChatGPT or Claude prompt to \u201cWrite me a WordPress plugin that calculates a unique price in the cart\u201d<\/em>, and the machine spits out the finished PHP code in seconds.<\/p>\n\n\n\n From the outside, programming seems to have become democratized. Business leaders, marketers, and enthusiastic hobbyists suddenly feel they no longer need expensive developers, as AI writes code, bash scripts, or pulls up the server instead. However, in my university teaching and senior development practice, I increasingly encounter the dark side of this phenomenon: the disastrous consequences of code generation without understanding.<\/strong><\/p>\n\n\n\n When a layman copies the AI-generated code into their website or server terminal and it runs seemingly flawlessly, they get an immediate sense of success. The button has become green, the form has been saved, the webshop is counting.<\/p>\n\n\n\n The problem is that AI \u2013 unless it gets a very strict, engineering-level context and architecture plan \u2013 always goes in the slightest direction of resistance. It delivers the fastest, most primitive solution that right at the moment<\/em> solve the task. It does not deal with what happens when a thousand people click the button at the same time. You don\u2019t care about memory leaks, code sustainability, and in many cases, security.<\/p>\n\n\n\n If someone is not familiar with the operating logic of the given framework (e.g. WordPress), the basics of object-oriented programming, or the rules of relational databases, it does not build a system, but glues fragments of code to each other.<\/p>\n\n\n\n A layman cannot tell AI not to create a separate SQL table for a WooCommerce custom campaign, but to use existing built-in functions. The result is a \u201cFrankenstein code\u201d full of redundancy, logical dead ends and code garbage. When a PHP or WordPress major version update comes in 6 months, this digital house of cards crashes in a snap with a loud 500 server error. And since the owner never understood the code, he has no chance of debugging.<\/p>\n\n\n\n The most fearsome aspect of AI-driven amateur development is cybersecurity. A user without basic IT knowledge will not notice if the generated code does not clean user data entry (sanitization).<\/p>\n\n\n\n He\u2019s happy to put the AI-written custom form into action, making it the perfect target for a SQL Injection attack. AI can write perfectly secure code, but for this, the prompting (questioning) person needs to know that request<\/em> adherence to security protocols and be able to verify that it has actually happened.<\/p>\n\n\n\n All this does not mean that AI is bad, in fact. As a developer, I also use local, uncensored models on my workstation on a daily basis, integrated into VS Code. But the approach is radically different.<\/p>\n\n\n\n AI isn't the captain, it's a brutally fast and smart co-pilot. I use it not to figure out the architecture for me, but to type routine tasks (boilerplate codes) faster on the stable foundations I design, or to help search for syntactic errors in a complex algorithm.<\/p>\n\n\n\n AI in knowledge acts as a multiplier:<\/p>\n\n\n\n Even though you have the world\u2019s most advanced code generation tool in your hands, if you don\u2019t know what you\u2019re building, you\u2019re just automating chaos. The basics of IT \u2013 the structure of HTML\/CSS, the operation of servers, the logic of networks and algorithmic thinking \u2013 are more valuable today than ever before. Because the task is no longer typing syntax, but quality assurance, architectural design, and judging whether the answer given by the machine is really good.<\/p>","protected":false},"excerpt":{"rendered":" In the past year and a half, we have witnessed a technological leap that has fundamentally changed software development. <\/p>","protected":false},"author":2,"featured_media":2287,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"slim_seo":{"facebook_image":"https:\/\/teszarypeter.hu\/wp-content\/uploads\/2026\/05\/Evolution-of-computation-and-AI.png","twitter_image":"https:\/\/teszarypeter.hu\/wp-content\/uploads\/2026\/05\/Evolution-of-computation-and-AI.png","title":"Amikor IT alapismeretek n\u00e9lk\u00fcl fejleszt\u00fcnk AI-al - Tesz\u00e1ry P\u00e9ter","description":"Az elm\u00falt m\u00e1sf\u00e9l \u00e9vben egy olyan technol\u00f3giai ugr\u00e1snak lehett\u00fcnk szemtan\u00fai, ami alapjaiban v\u00e1ltoztatta meg a szoftverfejleszt\u00e9st."},"_slim_seo_primary_term_category":93,"_slim_seo_primary_term_post_tag":0,"footnotes":""},"categories":[93],"tags":[],"class_list":["post-2330","publikacio","type-publikacio","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"openstation_lock":null,"openstation_contributors":[],"openstation_attached_media":[2287],"meta_box":[],"_links":{"self":[{"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/publikacio\/2330","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/publikacio"}],"about":[{"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/types\/publikacio"}],"author":[{"embeddable":true,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/comments?post=2330"}],"version-history":[{"count":1,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/publikacio\/2330\/revisions"}],"predecessor-version":[{"id":2331,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/publikacio\/2330\/revisions\/2331"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/media\/2287"}],"wp:attachment":[{"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/media?parent=2330"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/categories?post=2330"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/teszarypeter.hu\/en\/wp-json\/wp\/v2\/tags?post=2330"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}The illusion: \u201cIt works, so it\u2019s good\u201d<\/h3>\n\n\n\n
The Frankenstein Architecture<\/h3>\n\n\n\n
The Invisible Vulnerabilities<\/h3>\n\n\n\n
AI is actually a Multiplier<\/h3>\n\n\n\n
\n