{"slug": "ai-is-a-bad-tool", "title": "AI Is a Bad Tool", "summary": "A developer argues that AI is a bad tool for software development, citing its opacity and inability to produce verifiable code. The author claims AI-generated code cannot be reliably maintained or audited, making it a poor substitute for human engineering. The piece warns that reliance on AI may lead to irrelevant developers producing garbage code.", "body_md": "*Editor's Note*: friend of ByteCode.News Hideki Idoru submitted this for publication, and it has a lot of value even if not every point is agreed with: it's not difficult to find it's failure modes observed *widely* in the industry these days.\n\nAI is a bad tool.\n\nAt least, AI is a bad tool for *software*.\n\nI'll start with the positive side to get it out of the way. AI *can* be useful\nif you perceive it as a data distiller. Whereas before, you'd put a thing into\nyour search engine, click on the result that sounded most promising, then scan\nthe page for the info you're looking for and process it in a way you understand,\nAI -- if it's good and true -- condenses those steps for you. Indeed, search\nengines today try to close the gap by inserting an AI snippet at the top\nof their results, but the immersive part is your ability to follow up and\n*refine* the info even further.\n\nThis used to take a long time to do manually, and it's genuinely easier to have the machine do it for you. So it's not all bad.\n\nBut that's pretty much where it ends. If you use AI for anything else, and in particularly if you use it to generate code, you're wasting your time.\n\nBefore I go into why, I have to take a step back and talk about the debate\n*about* AI itself. It is often too emotional than it needs be. A lot of it on\nthe part of its detractors is driven by fear of losing their livelihood and\nbecoming essentially irrelevant. I don't think the emotions help, but\nthey do provide interesting insights into the human condition because, as I'm\nabout to show, the fear *is* real (but for a different reason).\n\nIn other words: yes, you're going to become irrelevant, and no, it's not\nbecause the machines will become too smart for you. It's because you produce\ngarbage code and they can do just *a little* better.\n\nThe reason AI is a bad tool is that generally speaking, it is *completely*\nopaque. A standard question one often hears is, \"who is going to maintain the\napp you had it build for you?\" Well, if you're fully onboard the AI train,\nyou'd say: the machine. If it built it, it should surely also be able to\nmaintain it. That's not false.\n\nThe real question is, who can verify that what the AI built is good and true? Recently, there's a lot of talk about AI allegedly finding security flaws in software. That is an unsubstantiated claim. As such, it would need to be verified by a non-machine, and arguably, the verification process would require the same amount of effort or more than would be required to find the issue to begin with.\n\nThe same logic applies to the app you have had the AI build for you. Who is\ngoing to verify that it is doing what it is supposed to? It might *look* like\nit is, but notoriously, *Schein* and *Sein* aren't the same thing. And lo: when\nwriting tests for existing implementations, AI is notoriously known for biasing\nthe tests to fit the implementation instead of blindly writing them from a\nspecification point of view. It doesn't solve the problem -- it just makes it\nlook like it did.\n\nAI being completely oblique also means that 'AI engineering' or 'prompt\nengineering' is a complete scam; same like SEO in the day, any claim of being\nable to manipulate a blackbox machine in some clever way is bogus. You have no\nway to establish correlation, and whatever patterns *you* might hallucinate\nabout however the machine works are unstable. In short: you don't have access to\nthe source code, and even if you did, you likely don't have the mental\nprocessing power to understand it, and even if you did, AI moves too fast for\nany patterns you might derive to be purposefully true. You're not inherently\nstupid; the machine was just built by very smart people who are so smart that\nthey likely don't fully understand it themselves.\n\nSo AI is a tool you cannot look into: a machine-realised form of \"trust me bro\". In that case, why is it so revealing when it exposes an ingrained human fear of being irrelevant and left behind? Why do you revolt against it much?\n\nBecause any programming task you have the AI do for you today is on account of\nyou not properly abstracting your work. If you have AI rename a symbol; well,\nthis is something your LSP should handle. If you have AI scaffold your project,\n*probably* the scaffolding is something your framework should take of. Every\nline of code that you have your AI produce is likely to *reduce* abstraction and\nincrease repetition. All the AI does is reveal the lack of proper abstraction\nin your stack. And the problem with that, for you, is that if the code were\nproperly abstracted, you probably wouldn't have a job, but as things stand, the\nmachine is becoming better than you at producing *unabstracted code*.\n\nIn other words, if all AI does is produce *trivial* code, then it should be\ntrivially abstractable. Were it to produce non-trivial code, which it doesn't,\nthat would beg the question *how* it did that based on its inputs, but that\nwould still gain you nothing due to its obliqueness and the fact you'd need to\ngo over something non-trivial yourself that you probably don't understand. It\neither solves non-problems, or creates non-issues.\n\nThe grand point here is that *most* jobs in software have been useless long\nbefore the advent of AI. AI just tore that mask off, and that is driving people\n*crazy*.\n\nSo where do we go from here? How to deal with the consequences of a software world that, accelerated by AI, will become a dead graveyard where no one has anything to do, because AI does all the useless, unabstracted work, and a select few geniuses operate above the aether?\n\nI unfortunately don't have a good answer to this. Maybe people need to go back\nto following their passion, instead of chasing the ghost of AI and its fake\npromise. Maybe being passionate about something you build, understanding it\nfully, owning it completely, *and* abstracting it properly so it never falls\nprey to the menace of AI, is the only way forward.", "url": "https://wpnews.pro/news/ai-is-a-bad-tool", "canonical_source": "https://bytecode.news/posts/2026/07/user-submission-ai-is-a-bad-tool", "published_at": "2026-07-13 19:51:15+00:00", "updated_at": "2026-07-13 20:05:14.598542+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-ethics", "ai-safety", "developer-tools"], "entities": ["Hideki Idoru", "ByteCode.News"], "alternates": {"html": "https://wpnews.pro/news/ai-is-a-bad-tool", "markdown": "https://wpnews.pro/news/ai-is-a-bad-tool.md", "text": "https://wpnews.pro/news/ai-is-a-bad-tool.txt", "jsonld": "https://wpnews.pro/news/ai-is-a-bad-tool.jsonld"}}