I Think I Have LLM Burnout Skip to main content<br>I use LLMs a lot. By current dev standards, my usage rate is probably average,<br>and my methods are probably primitive. I work on one task at a time and discuss<br>it with Claude Code (at work) or Codex (at home, for now). Sometimes, I let the<br>assistant write code, but I read the output thoroughly, understand it, and<br>revise it. I’m not in the deep end of autonomous agents or agent orchestration.<br>Still, I spend hours each day interacting with LLMs across work and home.<br>That’s a hell of a lot more than I did a few years ago, and I probably don’t go<br>a day without reading AI-generated text.
My job has changed from designing and writing code to designing code,<br>describing the design to an LLM, reviewing code the LLM produces, and then<br>finally writing code. The LLM steps expose me to approaches I might not have<br>considered or been aware of. I also feel more comfortable in areas where I<br>don’t have deep knowledge.
My main project right now is to establish a framework for large-scale,<br>unsupervised code generation in our codebase. When I’m not working with Claude<br>to create tooling, I’m sifting through the unsupervised agent’s (Qwen’s)<br>output. Either way, I’m reading LLM content.
If I want to know something, I’ll probably ask ChatGPT or read Gemini’s<br>overview unless I know what sites I want to check. I still have to fall back to<br>browsing when the LLM’s answer is wrong, but it’s good enough for many casual<br>queries, especially when useless AI-generated articles clutter the search<br>results.
It’s been this way for about a year, and I don’t see myself stopping. I feel<br>more productive with LLMs, and I think continually learning how to use them<br>effectively is valuable. However, my disposition has changed a bit in the last<br>few months. Some small part of me has started to dread reading LLM output<br>because I know what I’m going to find. False assumptions and hallucinations.<br>Emphatic, staccato fragments. ✨ Excessive emojis 🚀. It’s not<br>just me—these are real patterns (🤮).
On their own, none of these annoyances gets to me. Together, though, they’ve<br>gotten me sick of LLM writing in a hurry.
I’m not trying to condemn LLMs. Humans are fallible, too—we can be just<br>as unreliable or annoying. The problem is repetition. LLMs write in the same<br>style, and they make the same kinds of mistakes. Dealing with the same thing<br>over and over is wearing me out. I can use personalization features if the<br>interface offers them, but some idiosyncrasies seep through. And of course, I<br>don’t control the style of content generated by other people.
I don’t know how to deal with this feeling yet. I didn’t expect to be so<br>bothered by it. Frustration at a flaky tool is understandable, but the writing<br>patterns grind my gears, too. For now, I’ll grit my teeth and hope I don’t lose<br>my lunch.