Ask HN: SWEs how do you future-proof your career in light of LLMs?

I'm actually interested in what you think AI will do as this is quite vague.

> "AI" tools offer an opportunity to change the way we do those things.

The way I see tooling in programming is that a lot of it ends up focused on the bits that aren't that challenging and can often be more related to taste. There's people out there eschewing syntax highlighting and code completion as crutches and they generally don't seem less productive than the people using them. Similarly people are ricing their Neovim setups but that doesn't seem to add enough value to outperform people using IDE defaults.

Then software engineering tools like task management software, version control and documentation software are universally pretty terrible. They all "work" with varying foibles and footguns. So I think there is a massive advantage possible there but haven't seem real movement on them in years.

But LLM based AI just doesn't seem it, it's too often wrong, whether it's Slack's Recap or the summarizing AI in Atlassian products or code completion with Copilot it's not trustworthy and always needs babying. It all feels like a net drain at the moment, other than producing hilarious output to share with your coworkers.

If as a developer you are already reliant upon LLMs to write code or require use of abstractions that LLMs can write you are already replaceable by LLMs. As a former JavaScript developer this makes me think of all the JavaScript developers that cannot do their jobs without large JavaScript frameworks and never really learned to write original JavaScript logic.

That being said you can future proof your career by learning actual concepts of engineering: process improvement, performance, accessibility, security analysis, and so on. LLMs, so as many other comments have said, remain extremely unreliable, but they can already do highly repeatable and low cost tasks like framework stuff really well.

In addition to actually learning to program here are other things that will also future proof your career:

* Diversify. Also learn and certify in project management, cyber security, API management, cloud operations, networking, and more. Nobody is remotely close to trusting AI to perform any kind of management or analysis.

* Operations. Get good at doing human operations things like DevOps, task delegation, release management, 24 hour up time.

* Security. Get a national level security clearance and security certifications. Cleared jobs remain in demand and tend to pay more. If you can get somebody to sponsor you for a TS you are extremely in demand. I work from home and don't use my TS at all, but it still got me my current job and greatly increases my value relative to my peers.

* Writing. Get better at writing. If you are better at written communications than your peers you are less replaceable. I am not talking about writing books or even just writing documentation. I am talking about day-to-day writing emails. In large organizations so many problems are solved by just writing clarifying requirements and eliminating confusion that requires a supreme technical understanding of the problems without writing any code. This one thing is responsible for my last promotion.

And 3D animation still requires hand animation! Nobody starts with 3D animation, the senior animators are doing storyboards and keyframes which they _then_ use as a guide for 3D animation.

I think people are coping. Software engineering has only gotten easier over time. Fifteen years ago, knowing how to code made you seem like a wizard, and learning was tough - you had to read books, truly understand them, and apply what you learned. Then came the web and YouTube, which simplified things a lot. Now with LLMs, people with zero experience can build applications. Even I find myself mostly prompting when working on projects.

Carmack’s tweet feels out of touch. He says we should focus only on business value, not engineering. But what made software engineering great was that nerds could dive deep into technical challenges while delivering business value. That balance is eroding - now, only the business side seems to matter.