Writing with AI is sux
I stopped using LLMs to write blog posts and limited them to proofreading and presentation work.
In the past few months, I have tried to simplify and automate blog posting. During this process, I have created all kinds of tests:
- I created a fully automated workflow where, with a simple prompt, AI researched a topic and created everything, including the diagrams and tables.
- I created a semi-automated workflow where I used the /grill-me skill to figure out the content, outline it, and draft it, and eventually an LLM such as Opus 5 would write the final article (.mdx).
All of this is because I wanted to save time. For me, the blog is a way to show my interests, perhaps share interesting information, and store my public notes for later.
But the issue is that LLMs are just really bad at writing something more complex as a simple email. I am not a writer, but I have already crafted a lot of text. I don’t really care about writing style; I just want to share some of my ideas.
However, the issue I found with letting an AI write even a simple text is that alignment with my intent is almost impossible to achieve. Why? Because if I dictate what I want a post to be about, that is still just raw text, and it misses the process of crafting the article. If the raw text were exactly what I wanted, I would not need an LLM to write it.
Even the latest frontier model would use that information and rely on a lot of generalization to craft the text, causing it to lose its point, tone, mistakes, and, essentially, its value. (I am not sure if this post has value, but at least I went through the process.)
So I will follow what others do. I will use LLMs only to proofread and add HTML and Astro Islands elements to a post, but the text will be mine. I have removed my old posts.