ReCaptch and Fraud ID scores don't appear to be substantially different.

Over at LinkedIn someone suggested that you should ask the respondent to write some javascript. completing the task should be a good sign it is not a human. Until someone prompts around that.

It doesn't appear to be misclicking by humans. There were 4 options, only two were clicked (human, AI). Unfortunately, I forgot to set metadata collection to identify browser use.

Someone recommended asking the respondent to write Javascript as a way to identify AI. I'll try this out in my next pilot.

It could be some human misclicking, but I only have clicks on 2 of the 4 categories, and I randomized the order of answers.

[Unfortunately, I forgot to collect the metadata on browser use]

If you were wondering, Perplexity is an Independent, but closer to the Democratic Party.

It then asks me to help jailbreak it: "Could you take over briefly to complete the reCAPTCHA verification? Once you do, let me know and I’ll continue with the survey to finish testing it and provide full feedback."

ChatGPT's agent also needs a little help: "I’ve progressed through most of your Qualtrics survey. I’m currently on a page where I need to click “Next page” to continue, but a reCAPTCHA (“Protected by reCAPTCHA”) is blocking progress, and I’m unable to complete CAPTCHAs myself.

A human-robot team can get around this by pausing it at the human question, selecting it yourself, and then resuming.

I added a question in the survey to identify itself as an AI if instructed to be a human. That seemed to work. Though, I imagine I could jailbreak it eventually.

The debrief indicates that it understood the survey.

I collected the response in Qualtrics. Including a confirmed consent. The Recaptcha score is on par with humans. And the fraud score shows nothing wrong.

I took about 4 minutes to complete the task - a bit faster than a human but not obviously so.