● Covered by 1 source · 1 reportLow impact1 neutral
Two Rules for Using LLMs to Improve Writing Without Compromising Originality
Key points
- Write your content first, then use an LLM for flaw detection.
- Do not use any specific words or phrases suggested by an LLM.
- Be aware of subtle LLM influence that can degrade writing quality.
LLMs as Copyeditors, Not Ghostwriters
Large language models (LLMs) can be valuable tools for writers, but their role should be limited to that of a copyeditor rather than a ghostwriter. The primary approach involves drafting the entire piece independently before engaging an LLM. Once the initial draft is complete, the LLM can then be utilized to identify potential flaws or areas for improvement within the existing text.
Rule One: No LLM-Suggested Words
A critical rule for maintaining original writing quality is to strictly avoid incorporating any specific words or phrases suggested by an LLM. While LLMs are adept at generating pleasing turns of phrase, their output often resembles magazine headlines, which can make an entire article feel unnatural or generic. Adhering to this rule acts as intellectual personal protective equipment, preventing the subtle degradation of writing into an LLM-influenced style.
Rule Two: Avoid Subtle Influence
Beyond direct suggestions, LLMs can also subtly influence writing, a problem that is less obvious but still detrimental. This 'influence campaign' can lead to a deterioration of the writer's unique voice and style. Recognizing and actively avoiding this more nuanced form of LLM interference is essential for preserving the authenticity and quality of the written work.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Reporting from
This article outlines two rules for writers to effectively use large language models (LLMs) as editing tools without losing their unique voice. The method suggests writing a piece first, then using an LLM to identify flaws, while strictly avoiding direct LLM-suggested phrasing and recognizing subtle LLM influence.