One of the common conversations with friends lately is: how do you use LLMs? In the latest round, I mentioned that I used LLMs to motivate myself — and people were surprised. In turn, I was surprised they were surprised.

When comparing notes with other peers at work, this was a shared feeling: LLMs were useful for activating yourself. I also had read a report on how Anthropic’s engineers use Claude Code, and they share ideas along the same lines:

Some also said that the reduced “activation energy” of using Claude enabled them to defeat procrastination more easily, “dramatically decreasing the energy required for me to want to start tackling a problem and therefore I’m willing to tackle so many additional things.”

The science behind motivation

This feeling about the “activation energy” can be linked to how motivation works. Scientists divide motivation into two processes:

• what’s the cost-benefit ratio?
• is it worth starting?

When we deem the cost of an action higher than the benefit, our motivation to perform it is low, and vice versa.

The second aspect, while intuitively understood, wasn’t proved until a study published days ago. Researchers tested how monkeys performed (or not) some task, and they claim to have found the physical brain circuit that acts as the brake and some biochemicals that inhibit or release the activation.

In essence, what happens is that even in situations where we understand the benefits are high we decide not to do it because the “activation” causes some kind of stress — that’s what they call “the motivation brake”. The stress may come from some physical pain, or from negative feelings related to the task: self-doubt, pressure from schedules, self-imposed perfectionism, lack of tolerance to frustration, fear of failure, etc.

I’d argue that stress can also be situational: try doing anything after a copious lunch, dealing with something difficult at the end of the day, working when you have a cold, or coming up with sharp thoughts when you have sleep deprivation.

The practical advice from this study is that, depending on which circuit is involved in your lack of action, you may need to do different things:

• if it’s the cost-benefit ratio: increase the reward
• if it’s the activation trigger: reduce the stress related to the task

Which is in line with some known tricks to deal with procrastination: give yourself a reward after doing something unpleasant, time-box your efforts to reduce the stress associated with starting the task, etc.

Using LLMs

LLMs affect motivation in two ways. On the one hand, they reduce the cost of performing some tasks, impacting the cost-benefit ratio. On the other, they can be used to reduce the stress related to the task.

On the second point, one of the typical ways to reframe the negative emotions about a task is time-boxing it: “I’d give it just 15 minutes”. It’s easy to start if you focus on the process and lower the expectations. Another trick is asking yourself: “what’s the minimal thing I can do now?”.

It turns out engaging LLMs for this is useful as well. This is what I do, for example, when I need to review a pull request but I have brain fog. Instead of reading the code myself or even glancing at the long thread of comments, I ask Claude Code to read it all, and summarize it for me in less than 50 words. Then, I keep asking small questions until I get past the activation energy and I’m engaged with the task.

We often think about LLMs as tools for solving problems, but I find them just as valuable for helping us get started on solving them ourselves. The hardest part of any task is often just beginning — and having a tool that lowers that barrier makes it more enjoyable.