Question On My Job Application

When someone asks "Is it JavaScript or Python?" and the dev responds "I actually didn't write much code - just prompting" you know we've officially entered the AI era of programming. The follow-up comment "So is it javascript or python? Jesus fucking christ" is the collective frustration of every traditional developer watching their craft get reduced to chatting with an LLM. This is the new reality: devs are now prompt engineers who vibe-coded a rage/timing game by basically having a conversation with AI. The confusion about which language was even used is *chef's kiss* because it doesn't matter anymore - the AI wrote it all. Meanwhile, seasoned developers are having an existential crisis trying to figure out what stack was used while the prompt jockey is already shipping features. Welcome to 2024, where "I can code" means "I can write a really good sentence."

You fire up your AI coding assistant thinking you're about to conduct a symphony of perfectly generated functions. Two minutes in, you're sitting there like a caveman while the AI and your actual code are having a sophisticated discussion about why nothing works. The confidence-to-confusion pipeline has never been more efficient. At least the AI is polite about explaining why your original approach was fundamentally broken.

Running a local LLM on your machine is basically watching your RAM get devoured in real-time. You boot up that 70B parameter model thinking you're about to revolutionize your workflow, and suddenly your 32GB of RAM is gone faster than your motivation on a Monday morning. The OS starts sweating, Chrome tabs start dying, and your computer sounds like it's preparing for takeoff. But hey, at least you're not paying per token, right? Just paying with your hardware's dignity and your electricity bill.

Linus Torvalds just casually dropped the ultimate productivity hack: why write complete code when you can outsource it to your open-source community? The man literally emails code snippets like "hey, wouldn't it be cool if..." and waits for someone else to do the actual implementation and testing. It's the OG version of using AI to write code, except instead of LLMs (Large Language Models), he's using LLCs—Large Linux Contributors. The genius here is that he's not being lazy—he's being efficient. Why compile and test when thousands of kernel developers are ready to jump on your pseudocode? It's like pair programming, but you're the one drinking coffee while everyone else does the typing. The maintainer's dream: maximum architectural influence, minimum keystrokes. Honestly, building an entire operating system kernel by vibes and delegation is a power move that no amount of Cursor AI subscriptions can replicate.

The suspicion is killing you. That landing page with its sleek purple gradients and modern aesthetic... there's no way they built that from scratch. You just know they used Claude AI to generate it. The telltale purple branding, the too-perfect copy, the suspiciously on-trend design. But when your boss asks if competitors are using AI, you've got nothing but gut feelings and paranoia. No git commits to analyze. No source code to inspect. Just you, alone with your conspiracy theories about AI-generated marketing.

So AI is simultaneously going to steal all our jobs AND create a massive shortage of engineers to maintain the trillion-dollar pile of legacy code it's about to generate? The tech industry really said "let's speedrun creating our own crisis." Nothing screams job security quite like being told you're obsolete while also being desperately needed to clean up the mess. The real kicker? We're gonna need those 100,000 engineers to fix the AI-generated spaghetti code that's written in 47 different frameworks, uses deprecated libraries, and has comments like "// TODO: refactor this later." Spoiler alert: later never comes, and now it's 2035 and you're debugging agentic applications written by an AI that learned to code from Stack Overflow answers marked as "This worked for me in 2019."