My Test of 10 AI Content Detectors

Using artificial intelligence tools to generate organic-search content is debatable owing to Google’s evolving guidelines.

AI can produce quality text — articles, descriptions — but it’s not always accurate and usually detectable. Likely that content will become more accurate and less detectable. But the tools I’m aware of — ChatGPT, Jasper, others — while impressive, are not yet infallible.

Thus AI text detectors remain useful. In this post, I’ll test the detectors.

I started by entering this prompt into ChatGPT:

Please explain how AI-written content can be detected. Please explain as if you were a human being.

Here is ChatGPT’s response:

As a human being, I can tell you that AI-written content can be detected by looking for certain characteristics that are different from content written by humans.

One way to detect AI-written content is to look for unnatural or awkward phrasing. AI algorithms are not perfect and can struggle with making content flow naturally, which can result in sentences that are difficult to read or sound robotic.

Another clue that content was generated by AI is a lack of nuance or context. AI algorithms work by analyzing large datasets to identify patterns and relationships between words, but they may not understand the nuances of language in the same way that humans do. As a result, AI-generated content may lack the depth of understanding and context that human-written content can provide.

Additionally, if the content is generated by a particular software, there may be certain markers or characteristics that are specific to that software. For example, some AI-generated content may have a particular style or format that is consistent across multiple pieces of content.

Overall, while AI-generated content can be useful for certain tasks, it is important to be able to distinguish between content generated by humans and content generated by AI, in order to ensure accuracy and avoid misleading readers.

I then…