AI Writing

It's hard to write something that's easy to understand without sounding childish.

AI Writing Tools

QuillBot

AI Writing Benchmarks

Communication Bench

The problem with using AI depends less on how much you use it than on whether the communication is functional or relational.

Confessions of an Unrepentant Slop Snob

A framework for thinking about when AI involvement is additive or a violation

https://charity.wtf/p/confessions-of-an-unrepentant-slop

human likeliness

Altworld/Hemmingway-1 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

https://huggingface.co/Altworld/Hemmingway-1

Let the model act as a copyeditor

How To Write With An LLM

Two rules keep an LLM from pasteurizing your writing: never take a word it suggests, and never let it encourage you. Then hand it all the tedious work.

https://sockpuppet.org/blog/2026/09/17/how-to-write-with-an-llm/

A German Max Planck Institute study found that certain words frequently used by ChatGPT (e.g., delve, meticulous, underscore, comprehend, bolster, etc.) have notably increased in frequency in YouTube and podcast audio content since ChatGPT's release.

Humans Are Starting to Talk More Like ChatGPT, Study Claims

AI isn’t just getting into your writing. It’s also getting into your mind and then out of your mouth.

https://gizmodo.com/humans-are-starting-to-talk-more-like-chatgpt-study-claims-2000628916

ChatGPT Is Changing the Words We Use in Conversation

Words frequently used by ChatGPT, including “delve” and “meticulous,” are getting more common in spoken language, according to an analysis of more than 700,000 hours of videos and podcasts

https://www.scientificamerican.com/article/chatgpt-is-changing-the-words-we-use-in-conversation/

최신 LLM은 인간이 이해하기 쉬운 문장보다 정보 밀도가 높은 문장을 생성하는 경향이 있다. LLM 문장의 특징: 희귀한 단어 조합, 긴 문법적 의존관계, 명사 중첩, 생략된 관계대명사, 무생물 주어의 의인화 표현 등이 인간 글보다 자주 나타남. 영어 문장을 일본어로 번역한 뒤 다시 영어로 번역하면 복잡한 표현이 상당수 줄어듦. Claude Opus 5.5는 Opus 5보다 21개 비교 중 19개에서 이해하기 어려운 언어적 특징이 감소함. Human Comprehensibility를 별도의 Post-training Objective로 고려해야 한다

arxiv.org

https://arxiv.org/pdf/2610.29162v1

AI Writing

Let the model act as a copyeditor

Backlinks

Recommendations