Undetectable AI has become popular in academic and blogging circles as a way to circumvent false AI detection. It’s a quick and easy way to safeguard yourself against false positives that have already claimed the reputation of more than one student.
However, here’s an interesting dilemma: If it’s meant to hide AI writing using AI, how can you ensure that its outputs won’t be flagged as machine-generated? That’s the reason why we must test its output against the best AI detectors available.
Now, we’ve tested Undetectable AI against other detectors before. But what about its own detector? Will it pass its own test? Time to find out.
A Short Discussion on Undetectable AI’s Detector
We’ve had lots of Undetectable AI articles before like this one, and this one, and this one, oh and here’s another one. The list goes on. One feature that we’ve yet to highlight is its AI detector, or to be more specific, detectors.
Undetectable AI doesn’t really have its own detector. Instead, it aggregates the AI likelihood scores from eight different detectors, namely:
Undetectable AI also promises (and delivers) free re-rewrite if their output gets tagged as AI by one or more of those eight.
If you’re interested to learn more about the accuracy of each individual detector, I highly recommend reading our article where we’ve tested most of their accuracy. I know it’s a cliché line, but I promise, the answer might surprise you.
Undetectable AI vs. Its Own Detector
So, enough foreplay, let’s get into the nitty-gritty. For this testing, we’ll ask ChatGPT to write seven unique texts and then input it into Undetectable AI. Once it’s generated the output, we’ll check if Undetectable AI’s detectors flag their own output as AI.
Let’s get started.
Test #1
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 75% (6 out of 8)
Test #2
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Test #3
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Test #4
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Test #5
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Test #6
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Test #7
Original GPT Text
Tweaked Output from Undetectable AI
Undetectable AI Detection Score
Did it pass? Yes!
AI Detector Score: 100% (8 out of 8)
Results Tally
What Have We Learned?
If we’re to take these scores at its face value, it’s safe to say that Undetectable AI’s tweaking is incredibly effective against detectors. However, you should always check their output further as they use grammar errors to mimic human writing.
And also, there’s another elephant in the room that I’ve yet to mention. Scroll back up and look at the eight detectors that Undetectable AI use. Notice something out of place?
If you said “OpenAI,” you’d be correct. OpenAI discontinued their AI detector months ago and have famously regarded its detection as inaccurate. I personally don’t know where Undetectable AI sources its OpenAI likelihood score. But since it’s always outputting “human,” then it’s safe to assume that it just defaults to human regardless of the input.
This is actually just one of the inconsistencies I notice with this detector. Another is that when I input Undetectable AI’s output to one of their detectors’ official websites, it sometimes gives me a different result from what I see in the Undetectable UI.
Beyond that, we can conclude that Undetectable AI does remarkably well even against its own detector. If you’re interested in learning more about this tool, you can read more about it in our official review. Good luck!