"So everybody is trying to write content with AI these days. You have your popular tools, like ChatGPT, Gemini, and Claude. And then when you put your content in there, you give it a prompt, right, and the content that ends up coming out is just garbage, trash, absolutely unusable. And what I see most people doing is that they complain. "Why can't I get great content when I try to write with LLMs?""
"before we get into these tips, I want to just put a caveat. These tools, by themselves, won't make you a great writer. But they can help you get more writing work done. I say this because LLMs are garbage in and garbage out. They cannot create authority. They cannot create expertise. They swallow up the whole internet and are only capable of giving out the quality that you put in. So the only way for you to get good quality from them is for you to be an expert writer who understands storytelling. Got it?"
"The first thing you want to do is to create a training document that you will feed it as an example. So let's say I'm trying to write a blog post, right? If I'm trying to write a totally dashing blog post that has a strong editorial voice, I'm going to pick one of the articles I've done in the past that was a very similar style, and I'm goi"
LLMs can produce unusable “garbage” content when prompts and inputs are weak, because they cannot create authority or expertise on their own. Quality depends on the quality of what is provided and on the writer’s skill in storytelling. Effective use starts with creating a training document that supplies examples of desired style and editorial voice. Guardrails help constrain outputs to relevant facts and formats. Storytelling techniques guide structure, clarity, and engagement. Using these practices together improves the usefulness of generated drafts and increases writing productivity while still requiring human expertise to finalize and validate content.
Read at Moz
Unable to calculate read time
Collection
[
|
...
]