Cracking the Code of AI Writing

Author(s): Shreepada Rao

Originally published on Towards AI.

How to Spot Robot Text and Make Yours Human Again?

This member-only story is on us. Upgrade to access all of Medium.

One of the interesting impact of AI stated by Forbes is : AI will allow more human stories (and brands) to stand out

While AI will enable businesses to produce a lot of content, companies that are creative and spend time producing standout content will rise to the top. Producing content that involves human stories, includes more detail than AI-generated content, involves multiple types of media or has a creative angle will beat the AI-generated content in search, social and with actual humans.

This brings a lot of opportunities to content creators in Medium and outside this environment to write and share their stories. It creates a new necessity to human-written stories with people and first-hand experience. I will walk you through the most common patterns of AI-written content.

Here are my handpicked patterns of AI-generated phrases and semantics, most of which I have picked from Medium. Some typical characteristics include:

1. Overuse of Transitional Phrases: AI models frequently rely on dry phrases like → “In addition, Furthermore, Moreover, For instance, In conclusion” and so on to connect ideas.

2. Repetitive Sentence Structures: Generates text with repetitive sentence structures, like “Subject +… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI