The age of token efficiency, the age of libraries — GolemUI Blog

Not so long ago, six months, perhaps, I was seriously convinced that AI would not replace us, the programmers. It would just help us; it would be our assistant. Back then I was mostly firing off one-off prompts in ChatGPT to help me with the odd algorithm, but to my delight, I still hand-crafted nearly all of my code.

Six months later, I’m not sure I can do my daily job without Claude. And I’m not alone: 84% of developers now use or plan to use AI tools, and as far back as February 2023 GitHub was already measuring 46% of the code in Copilot-enabled files as AI-generated, with its CEO predicting 80% “sooner than later”.

Fifty developers, one answer<br>Section titled “Fifty developers, one answer”

I got to test this against real people recently at DevBcn, where we were presenting GolemUI. I made a point of asking every single developer who stopped by our booth how they were using AI.

My deeply unscientific poll, around fifty developers from different companies and different parts of the world, yielded some genuinely scary uniformity. They basically all said the same thing:

“Nowadays I mostly write specs/prompts, and review PRs.”<br>Around fifty developers, different companies, different parts of the world. Basically one answer.

This lines up with Gartner’s prediction that by 2028, 90% of enterprise software engineers will use AI code assistants, up from under 14% in early 2024, with the developer’s role shifting from implementation to orchestration.

84% of developers use or plan to use AI tools Stack Overflow 2025<br>46% of code AI-generated in Copilot-enabled files, as early as Feb 2023 GitHub<br>90% by 2028 enterprise engineers using AI assistants Gartner

Not sure about you, but for me, after almost 30 years of writing software (yes, I’m old!), this is a little sad. Though I’m afraid it’s only sad because it means the industry is going through some major changes, and we humans don’t like change. So I, for one, would like to stay positive and believe this might turn out to be good, hopefully in the long run.

Will it? The answer probably depends on your favourite AI YouTuber.

The age of token efficiency<br>Section titled “The age of token efficiency”

But for you and me, the people working in this industry right now, where does this leave us today, not in five years?

Companies are starting to move on from all-you-can-eat tokens to something far more metered and corporate. Gartner forecasts worldwide AI spending to hit $2.5 trillion in 2026, up 44% in a single year. Most of that is infrastructure rather than your token bill, but it is exactly the kind of number that makes finance departments start asking questions further down the chain. And “all-you-can-eat” quietly becomes:

“How are you using your tokens? Are you using them efficiently?”<br>Sooner or later, someone is going to ask.

We are about to enter a world of wild metrics, built around two numbers:

Token cost per feature.

Trust % in the code generated.

The first one you can at least put on a dashboard, even if nobody will ever agree on what a “feature” is. The second one is the real trouble: trust is basically unmeasurable from inside your own walls. You can only measure trust in code if you know the area better than the AI does, and nowadays that tends to happen only if you are an industry expert in it.

Trust, the elephant in the room<br>Section titled “Trust, the elephant in the room”

Trust is, in my opinion, the elephant in the room of modern AI. Let me circle back to something I said at the beginning:

“I’m not sure I can do my daily job without Claude”

That line deserves more nuance. Yes, I depend on Claude to help me, but whether I can trust what it does comes down to one question: am I an industry expert in the area it is working on? That question splits my work in two, based on whether I care HOW something is done versus WHAT it achieves:

My core purpose: the thing my business actually delivers, the area where I am the expert. There I care about the HOW as much as the WHAT.

Everywhere else, I am not the expert, and I mostly care about the WHAT.

Basically, when working with GolemUI source code, I know I have the upper hand. I ask Claude to help me, but Claude is mostly a subordinate that reports to me.

Are you an industry expert in all the areas where your AI is writing code for you?<br>How can you trust, then?

Now, when I have to update our website, I care mostly about the WHAT. The website matters, but it is not my core purpose, and nobody is expecting me to be an expert in marketing sites.

The trust problem lives in that second bucket. With AI, you can code areas of the app you would never have been able to touch before, areas where nobody would call you an industry expert, so how are you supposed to trust something you don’t fully understand?

What % of trust do you, the human, have in this code?<br>And before you say it: yes, tests, obviously. But tests verify the WHAT. They...