"LLM paragraph will register to much of your audience not as writing but as output"
The best advice for writing for other humans is: don't use LLMs.
If you're writing for machines, liking coding, then fine go for it. If you're writing for processes with formal highly structured content like manuals, specifications, form content, procedures, information, that sort of thing, then also ok to use LLMS. But if you're writing for a human mind to ingest and extract meaning from, then LLMs are poison.
You just should not do things that human beings are good at with automated processes. Things such as: creative writing, painting, dancing that is not pre-programmed, going with the flow, living the moment, having sex, wrestling, cooking, acting, connecting with your loved ones... and so on.
Word chains these programs produce are inherently meaningless. They do not feel so, because WE people are amazing at bringing meaning to any old string of symbols: <a href="https://www.ubu.com/sound/lin.html" rel="nofollow">https://www.ubu.com/sound/lin.html
They are very useful machines indeed, but they do not help you write well. They mathematically cannot. They just try to guess what is the next tokern you might want to read.
Eddy_Viscosity2 · · focus · HN ↗
The best advice for writing for other humans is: don't use LLMs.
If you're writing for machines, liking coding, then fine go for it. If you're writing for processes with formal highly structured content like manuals, specifications, form content, procedures, information, that sort of thing, then also ok to use LLMS. But if you're writing for a human mind to ingest and extract meaning from, then LLMs are poison.
delis-thumbs-7e · · focus · HN ↗
Word chains these programs produce are inherently meaningless. They do not feel so, because WE people are amazing at bringing meaning to any old string of symbols: <a href="https://www.ubu.com/sound/lin.html" rel="nofollow">https://www.ubu.com/sound/lin.html
They are very useful machines indeed, but they do not help you write well. They mathematically cannot. They just try to guess what is the next tokern you might want to read.