AI Automated Engineers - Are We Doomed?

Not long ago, AI experts predicted that Software Engineers would eventually be automated by AI, just like many other professions. With the release of Devin, the first publicly introduced AI Software Engineer, the race has started, and there's been a lot of buzz (an interesting demos!) about it. Many developers, like other non-tech professionals, have started to worry.

Now, the question is not when, but how much and to what degree our jobs will be replaced by AI.

I've covered some of these topics in a past blog post, but as AI development has progressed many more thoughts have come to mind, I've discussed this topic with many people, and tried to be as updated as possible with the latest news so this is an updated and more comprehensive version of my thoughts on this topic.

The State of Software Engineering Automation

It all started with the release of ChatGPT at the end of 2023. It seems like this event was decades ago, but as a famous politician once said, "There are decades where nothing happens; and there are weeks where decades happen. (V. Lenin)". This is definitely the case. We were all amazed at how this chatbot could answer almost any question appropriately. For us engineers, it meant we didn't have to rely solely on Stack Overflow or other sources when googling, but rather use this tool as a comprehensive assistant to help us understand any concept or bug related to our software.

Not long after ChatGPT, GitHub Copilot was released. This was the second big step for engineers to have an AI tool directly embedded in our source code that could help us predict the next lines of code when given enough context. Eventually, Copilot Chat was also released, which, along with regular Copilot, was a perfect combo that gave us an extra productivity boost when writing or understanding our code.

Many other ChatGPT-like competitors have launched, like Claude, OLLama, nGrok, to name a few. We have almost daily breaking releases of new AI products that could affect how we work. The investment pace in AI is intense as venture capitalists work to beat one another, seeking big returns. This means a massive number of new AI tools are still in development and will potentially impact our work when released.

Can Developers Be Fully Automated?

That depends on the type of developer. This is a question that has been asked for a long time regarding many other professions. For example, some years ago when AutoCAD was released, many architects worried about their jobs. However, the reality is that AutoCAD didn't replace architects, but rather made them more productive and allowed them to use their energies on more creative tasks, rather than spending time drawing their concepts. While I think AI tools will have a bigger impact than any software tool released before, I believe to some degree, the same will happen with developers.

Some types of developers may be automated, for example, those who turn Figma designs into HTML or create simpler landing pages, and other similar tasks where the work involves using a few technologies for initial projects or proofs of concept will be the first to go. However, most of us developers with some years in the market know that a software developer is not a one-tool professional. We have to deal with people from different teams, several technologies across different versions, and generally, deal with problems that humans will (hopefully) only be able to solve. Even when existing full automation solutions are available now, they are not enough for handling some issues that machines can't solve. For example, Musk automated almost completely one of Tesla's gigafactories and had to roll back that decision as many issues arose where the machines couldn't solve problems that humans could.

Does the fact that AI tools partially replace us mean we'll have less work? Yes, definitely. We will be super-powered professionals who need less time to complete our work and therefore should be able to have more workload. No more time spent on stupid bugs caused by typos or unspotted silly errors, and more time on things that matter: architecture design, UX, business overview, best practices and patterns, etc. This twit from the Andrej Karpathy exdirector of AI in Tesla makes a great analogy with automated driving. Will there be fewer open positions for developers? Possibly; if more work could be done by fewer developers, why would any sane company overhire? The bright side is there's been a lot of discussion about potentially reducing the workweek for all tech developers, as discussed in this video. Even Musk has talked about a universal income for all humans since the decreased workload will give us less chance to work and earn money.

Finally, I think humans will still need to understand the basics, like a professor at my university once told me: "There are tools that already do this automatically, but to use them properly, you have to understand where the output comes from."

What About the Government?

Will they allow this flood of AI tools to replace workers worldwide? While highly criticized, the EU has been the first to start regulating AI as they consider some sensitive tasks should not be done by AI, regulate fake media content, and prevent uncompetitive actions by tech companies. They may also enforce companies to eventually reduce working hours and provide welfare for reduced salaries caused by lesser billed hours. Governments finally stepping in to enforce the correct use of AI will be crucial in determining the potential impact (positive or negative) on humanity. At this moment there's no regulation in place for them, therefore companies release them without any responsibility of potential harm they could cause, which in my opinion is a very dangerous situation and should be eventually regulated by governments. Here's an interesting podcast of an AI regulation advocate exposing why the Wild West state of product releases should be stopped.

It is widely known that some organizations like educational institutions (see here) and private companies are blocking the use of AI tools on their networks, and there is wide discussion about the ethical implications of using AI tools and how they could be correctly used. While AI offers potential benefits, there are valid concerns around academic integrity, data privacy, and responsible deployment that need to be addressed. My father is involved in Higher Education and this is a topic that we've discussed at length and there's no strategy to deal with it yet. The velocity of AI improvements is so high that it's hard to keep up with the latest tools, their implications and potential regulations.

What Should I Do to Protect Myself Against AI Automation?

• Don't over-specialize: Unless you want to become an expert in one single technology, over-specializing is probably not the best option since AI would likely beat you in all ways. "In a wicked world, relying upon experience from a single domain is not only limiting, it can be disastrous." - David Epstein
• Become a generalist: For me, this is the most viable option. Increasing your range of tools will make it very difficult for AI tools to replace you, since most will be made for solving specific problems. We've seen that existing models perform above average—sometimes better than most ordinary people on any topic you have in mind. However, only specialized AI tools are becoming the real threat to certain professions. This makes sense since most startups (not even OpenAI or other tech giants) don't have the scale to do everything perfectly. There will be different winners in each field or customer problem, therefore being a generalist is the way to go.
• Become the master of the threats: By threats, I'm obviously referring to the AI tools. Learning and understanding these tools in detail will allow you to control those tools. You could become an in-demand developer if you become proficient with them. You don't have to become an AI scientist or similar. For example, I'm learning how to implement Langchain into existing code bases to solve complex problems that would otherwise have required very difficult algorithms, thus adding AI value to existing products.

Wrapping Up

The days when software engineers were the untouchable professionals with the highest salaries and best perks are long gone. We will be impacted (we've already been) by AI. The bright side? Opportunists and people who were around only for the good salaries will be out, relieving the pressure for all those developers passionate about software, with incredible tools to make their job much easier and enjoyable. The downside is we'll probably earn less money for doing what we love. Who knows, maybe less competition from those quitters will prevent salaries from dropping too much? In my case, I wasn't part of that cohort with awesome salaries from 10 years ago, so I'm kind of used to having a decent wage while working on exciting things I love doing.

I think of this as an era similar to the industrial revolution, which brought incredible tools that made life easier for many people and freeing them from repetitive tasks and increased the productivity of the world. While that revolution also brought a lot of pain and suffering to many people, it also brought a lot of opportunities for those who were able to adapt to the new times.

Cheer up! Rather than adopting a Neo-Luddite mentality and cursing the inventors of these tools, we should be happy to live in a time when they've just been released when we're still young and able to adapt to them and we still have a lot of freedom to use them in our favor. Some similar might probably never be repeated, and those who are one step ahead of the pack could forge a very bright future for themselves and their loved ones.