







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.

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?

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.

Who Needs an LLM to Program an LLM?
A rank-one weight edit built from a model’s own matched pairs and a linear program, with no language model anywhere in the loop.


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.


Hallucinations in code are the least dangerous form of LLM mistakes
A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
Alignment Is Proven To Be Solvable
That LLMs understand natural language as well as they do should dramatically change our understanding of the problem.

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 …
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.
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…
Vim anti-patterns | Arabesque
The benefits of getting to grips with Vim are immense in terms of editing speed and maintaining your “flow” when you’re on a roll, whether writing code, poetry, or prose, but because the learning curve is so steep for a text editor, it’s very easy to retain habits from your time learning the editor that stick with you well into mastery. Because Vim makes you so fast and fluent, it’s especially hard to root these out because you might not even notice them, but it’s worth it. Here I’ll list some of the more common ones.

