---
format: "aidr-story-markdown/v1"
id: "cdd7b7c92bebb827ab7a0643ee97dfc646464e1e72f961aef0b9dcc903205d4a"
canonical_url: "https://aidr.today/cdd7b7c9?lang=en"
title: "Reducing the cognitive load of AI changes"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-01T12:57:19.000Z"
category: "Models"
topics: ["coding"]
source_urls: ["https://amoffat.github.io/blog/cognitive-load.html","https://lobste.rs/s/iwvjr0/reducing_cognitive_load_ai_changes"]
summary: "When reviewing large amounts of AI-generated code, I often find that the LLM chooses terms for abstractions that do not always map to my own choices. For instance, what it may call a MutationIntent might personally be more natural to me as an EditRequest . Because the LLM's choice of words is not my ideal choice, I have to do a mental lookup of what it means every time I see it, which adds cognitive load. This may seem like a small friction, but the cognitive load accumulates when considering how dozens of new terms interact in unfamiliar code. I can only hold a finite number of these semantic lookups in my head before I start misinterpreting how things work. To minimize this, before review, I post-process AI changes with this prompt: I then go through and confirm term choices. The AI does find-and-replace everywhere, including documentation. The resulting code is much easier to review because now it's written more like it came from my brain."
---

# Reducing the cognitive load of AI changes

> [Open the canonical story](<https://aidr.today/cdd7b7c9?lang=en>)

**Published:** 2026-10-01T12:57:19.000Z
**Category:** Models
**Topics:** coding

## Summary

When reviewing large amounts of AI\-generated code, I often find that the LLM chooses terms for abstractions that do not always map to my own choices\. For instance, what it may call a MutationIntent might personally be more natural to me as an EditRequest \. Because the LLM's choice of words is not my ideal choice, I have to do a mental lookup of what it means every time I see it, which adds cognitive load\. This may seem like a small friction, but the cognitive load accumulates when considering how dozens of new terms interact in unfamiliar code\. I can only hold a finite number of these semantic lookups in my head before I start misinterpreting how things work\. To minimize this, before review, I post\-process AI changes with this prompt: I then go through and confirm term choices\. The AI does find\-and\-replace everywhere, including documentation\. The resulting code is much easier to review because now it's written more like it came from my brain\.

## Sources

- [Story source](<https://amoffat.github.io/blog/cognitive-load.html>)
- [Discussion](<https://lobste.rs/s/iwvjr0/reducing_cognitive_load_ai_changes>)