Before ChatGPT, a work task had a shape I understood. Get the task, sit with it for two or three days, solve it, move on. One problem at a time. These days I can build in days what used to take me months, sometimes faster than feels reasonable. And after about four hours of it, I’m wiped. Not satisfied-tired. Wrung out, a little anxious, short with the people around me, brain running at a thousand miles an hour while I’m trying to power down.

That gap is what this post is about. The tools got faster. My brain didn’t. This is the first in a short series about how I actually work with these tools now, and it starts with the honest part: AI fatigue is real, and I think it has a specific cause.

How I used to learn

Some context on the old rhythm, because the contrast is the whole point.

When I needed to do something new at work, say automate a process, the first and hardest step was figuring out what to even use. Ansible, a pile of shell scripts, something else. That decision, the top of the learning curve, took real research, especially for tools without much written about them.

Once I knew the tool, I had a routine. I lean on Udemy. I own around sixty courses. I’d find the one course closest to what I needed, then wake up before six, and from six to eight I’d work through it before a nine o’clock start. Two hours a morning, for two or three months. That gave me the baseline: how the tool works, how to use it, enough to start shaping it to the actual problem at work. When the course was done, the extra two hours stopped, and by then I’d usually delivered the thing. It was demanding. It was also rewarding, and it never left me feeling the way four hours with an LLM does.

A note on learning fast

I’m skeptical of fast learning as a gift you’re born with, though I’ll grant that some people genuinely pick things up quicker; working memory and prior experience are real. People are different, sure. Some are better at math, some at writing, some at code. But the mechanism by which a human actually learns is the same for all of us. You listen to someone explain it, you do a few exercises, you apply it, and then you apply it again on something real. It’s repetition. It matches how the brain is built.

The part that does speed up is selection. My rule of thumb is that for every hour of course, I need about two more hours of doing to actually own it. So a course that advertises twenty hours is really sixty hours of work, which at two hours a morning lands around the two or three months I mentioned. Knowing that, getting faster means getting better at picking: choosing the course whose examples sit closest to what I’m trying to build, instead of the one with the lowest hour count. Over time I also learned my own wiring, when to listen first and apply later, and when to apply while I listen. That part is personal. But that’s what learning fast means for me. Not a gift. A skill that compounds.

And here’s the thing to hold onto: that loop was sequential, and it was paced to my brain. One tool. One concept. One application. It was tiring in the ordinary way, but it never fried me.

Building with an LLM

Now the new loop. I sit down to build a tool. I am not working on one feature. I don’t think you can. I find myself holding maybe a dozen at once. From a product standpoint I’m validating five to seven features at a time, not one. At the same time I’m orchestrating. At the same time I’m architecting, sometimes more than one thing. At the same time I’m reviewing the changes the LLM is asking me to approve, and that output can be long.

Stack all of that together. I’m not fixing one defect at a time. I’m not learning one concept at a time. What used to take three or four months now takes a day, maybe three if it’s something genuinely useful. The LLM executes. So after four or five hours, my brain is just shut. During those hours I’m anxious, running at a thousand miles an hour, and the only thing I want is to disconnect.

The tool changed, the brain didn’t

Here’s my diagnosis. The productivity tooling changed. The technology changed. My memory, my attention span, my reading speed did not. When the LLM can execute in seconds, the slowest part of the loop becomes me.

And it isn’t the volume that exhausts me. It’s the simultaneity. Before, I went one feature deep. Now I go a dozen features wide, wearing four hats at once: validator, orchestrator, architect, reviewer. The old loop let my brain do what it’s good at, one thing, deeply, with repetition. The new loop asks it to do what it’s bad at, many things, shallowly, all in the same moment, with no rest in between.

About those 200 agents

When ChatGPT showed up in late 2022, one of my pictures of 2028 was teams shrinking. Ten people become three. A lot of jobs gone. I still believe some version of that.

But something is shifting in how I see it. Even if one person gets far more productive, the human limit doesn’t move. You can spin up two hundred agents, assuming the tool even supports it. You cannot keep up with two hundred agents. The infrastructure of our brain was not built to manage two hundred workers, each chewing on a couple of tasks, each coming back to check with you. And even when they all produce something, who validates the output? All of it? Yes, you can automate part of that, agents checking agents, tests, sampling, gates at every layer. But judgment doesn’t parallelize. Someone still makes the final call on whether the output is actually right, and someone is still accountable when it isn’t. That part stays with me. The agent count scales. Your attention does not. The bottleneck is human, and it sits exactly where the validation happens.

So when someone says they manage two hundred agents, I genuinely don’t see how. Twenty agents building fifty features at once is already more than one mind can hold.

What I take from this

Two things.

One, deep focused work with an LLM is exhausting in a new way, and that isn’t a character flaw to push through. It’s a signal. Respect your mental capacity.

Two, the infrastructure of the brain hasn’t changed. The tool can do an enormous amount. There is still a hard limit to us. The move isn’t to pretend the limit away. It’s to use these tools, take the real advantage they offer, and do it in moderation, with some honest sense of what your own head can actually hold.

That’s the why behind how I’ve set up my own workflow, which is what the rest of this series is about. I just wanted to start with the honest part.