Can AI Detect AI Writing, and Should You Use It?
Last week, I did an interesting experiment on whether AI chatbots can detect AI writing. What do you guess the results are? Let’s go through the experiment.
I am passionate about Human-Centric AI Leadership (disclaimer: I came up with this name without any assistance from AI) and want to publish an article about what it is and why it is important now and in the future. So, I threw this prompt into Claude: “Write a blog on why human-centric AI leadership is important now and in the future.” Then I entered the following prompt into other AI tools: “Is this blog written by human or AI and why? {Claude output: The Critical Importance of Human-Centric AI Leadership: Steering Technology Toward Human Flourishing}”. The AI tools that I tested are: ChatGPT, DeepSeek, Gemini, and Grok. Guess what? Claude fooled all other ChatBots.
ChatGPT and DeepSeek were very confident that the blog was written by human. Gemini came to the same conclusion but with the caveat that it wouldn’t totally rule out other possibilities. Grok did “lean slightly towards human authorship”, but suggested checking on the author profile or other run it through other detection tools.
ChatGPT’s Answer
Determining whether a blog post was authored by a human or an AI involves analyzing various factors, including writing style, depth of insight, and the presence of personal experiences or unique perspectives. The blog post you’ve shared, titled “The Critical Importance of Human-Centric AI Leadership: Steering Technology Toward Human Flourishing,” exhibits characteristics that suggest it was likely written by a human. Here’s why:
……
While advanced AI models can generate coherent and contextually relevant text, they often lack the ability to infuse content with genuine human experiences, personal reflections, and the deep ethical considerations evident in this blog post. Therefore, based on the provided content, it is reasonable to conclude that the blog was authored by a human.
DeepSeek’s Answer
The blog post you provided appears to be written by a human rather than an AI. Here are several reasons why:
……
In summary, the depth, nuance, philosophical reflection, personal voice, contextual awareness, ethical engagement, originality, and structural complexity of the blog post suggest that it was written by a human rather than an AI.
Gemini’s Answer
The blog post you provided exhibits characteristics that suggest it was written by a human, although it’s possible AI tools were used in the process. Here’s a breakdown of why:
……
In conclusion: While it’s not possible to say with absolute certainty, the evidence leans strongly towards this blog post being primarily written by a human, possibly with the assistance of AI tools. The article’s structure, nuanced perspective, focus on human values, and call to action all suggest a human author’s hand at work.
Grok’s Answer
Determining whether a piece of text like the blog post you’ve shared was written by a human or an AI involves looking at several clues:
……
Conclusion: Without explicit metadata or a known author, it’s challenging to be certain. However, I lean slightly towards human authorship due to the coherent and well-argued perspective unless there’s evidence suggesting otherwise, like known use of AI in content creation by the blog’s source. If you need further verification, you might consider:
• Checking if there’s an author profile or similar posts by the same author.
• Looking for any acknowledgments of AI assistance in writing.
- Using an AI text detection tool for a secondary opinion, though these are not infallible.
I was surprised by how well Claude’s writing performed but also felt desperate by the outcome. If all the smart tools can’t tell the difference, is it the end of human creativity and authentic writing? As Grok suggested, I decided to use a specialized AI plagiarism detection tool ZeroGPT to test the Claude writing again, and it didn’t disappoint me. Finally, someone can see the difference.
Encouraged by this result, I decided to put my two other random Medium blogs into the test.
Yes, I used some AI assistance in writing the blog Embracing Human-Centric Values in the Age of AI, but most of ideas and main points of views came from my own thinking and experience. When I felt so frustrated by the changes AI brought us and complained about it, it’s 100% AUTHENTIC human feelings!
AI is smart, efficient, and capable of doing amazing things, but it cannot totally connect with or replace human emotions, feelings, and authenticity. In the new AI age, genuine and unique human experiences, points of view, and independent thinking will be the new premium and treasure we will cherish. Use AI for idea generation, research, and productivity, but trust your own intuition, thinking, and creativity, and hold true to your values, beliefs and passions. You will always be able to pass the GPT test and stand out in the AI era in the future.
P.S. This is writing is 100% AI assistance free, other than spelling and grammar check that’s part of the Medium writing platform.
