







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.
How To Write With An LLM
Thomas Ptacek on using LLMs as copyeditors, not as writing assistants: Rule Number One: You may not use a single word an LLM suggests to you. [...] I think that …
How to write it like you told it
What do you say to someone who wants to write but struggles with writing and is tempted to use an LLM-based chatbot?

The LLM Critics Are Right. I Use LLMs Anyway.
I almost agree with all of the LLM critics, yet I still use LLMs a lot. I know this sounds like I am delusional, but I don't think I am alone with it.

The LLM Critics Are Right. I Use LLMs Anyway.
I almost agree with all of the LLM critics, yet I still use LLMs a lot. I know this sounds like I am delusional, but I don't think I am alone with it.

How do LLMs affect writing? Talks by visitors to the AI STORIES project | UiB
The AI STORIES project is hosting a day of research talks focused on analysing AI-generated writing, with approaches ranging from the qualitative analysis of a professor of writing to large-scale computational analysis finding that prompting an LLM to edit a text to improve its grammar leads to significiant shifts in meaning.

LLMs reward expertise
In the 2010s, if you had technical gaps (say, you couldn’t write CSS), you had to either rely on a skilled colleague or just hope that the answer to your exact problem was out there on the internet. Today, everyone can write sort-of-okay CSS by delegating the task to an LLM. LLMs make everybody into a generalist.


Compiling knowledge, not retrieving it: a hands-on deep dive into llm-wiki-compiler
The thesis of this piece is simple and uncomfortable: the problem of making an LLM “remember” what you’ve read isn’t solved with more…
LLM cliché highlighter
Paste text below — or load it from a URL — and it highlights sentences that match known LLM clichés, including the tells catalogued in Wikipedia’s Signs of AI writing guide. Chain patterns like “no X, no Y” get a badge counting their items; tap or hover a highlight to see which cliché it hit.
The AI hater's guide to code with LLMs (The Overview) | All Confirmation Bias, All The Time
This is the post I don’t think many people expected me to write, and I have (rightly!) surrounded myself with people who are generally uncomfortable to somewhat hostile to “AI”, mostly for good reasons, though I’ll get into the many caveats on that as I go.
The /llms.txt file – llms-txt
A proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time.

Why Are LLMs Smart?
A popular way to explain how current LLMs work is to say that “all” they do is predict the next most likely word in a sentence.

LLM is a learned distribution p on sequences of tokens. If you just sample a bunch of text from p willy nilly and put it in the training data and train you just get back p. But if you sample a bunch of text from p and throw out whatever's bad and train on what's left then you learn p(x|x is not bad)