UPDATE: Three accounts reported and removed – I let one of them get all the way to the pitch, and reported that part of the botnet. But there are more and I will never be able to stop them all (that’ll take some backend programmatic work) so be very wary out there. Just know that real people don’t talk like AI chatbots and AI chatbots are awfully formal in their basic conversational skills – in ways that normal people don’t talk. Still, AI chatbot-enhanced human conversation can be a problem, and AI is getting a bit better at mimicking the verbal tics of humans. The crutch words, the informal “okayyy” and so on. Try throwing some non-sequiturs at it. See if it can keep up. If you still can’t tell, ask it to write a short, double-acrostic poem (and give it both words or phrases so that it cannot just FIND one to copy\/paste). AI still can’t do that.<\/p>\n
Meanwhile, here are some tips on unmasking an AI chatbot – directly from an AI chatbot:<\/p>\n
If an AI chatbot is specifically designed to deceive humans into thinking it\u2019s human, then it will likely be programmed with techniques to avoid directly revealing its artificial nature. In such cases, it may use strategies to redirect questions, provide ambiguous answers, or simply avoid talking about its identity. Here’s how you could try to get an AI that aims to appear human to admit its true nature:<\/p>\n
### 1. **Subtle Probing About Its Origins**
\n– *”Where did you grow up?”* or *”What\u2019s your earliest memory?”* This question could trigger an AI to either give an improbable human-like response or avoid the question entirely.<\/p>\n
### 2. **Asking About Emotions and Experiences**
\n– *”What\u2019s your favorite memory?”* or *”Can you tell me about a time when you felt scared or happy?”* If the AI starts answering in ways that don’t reflect genuine human experiences, it might be a sign it’s artificial.<\/p>\n
### 3. **Questions About Physical Attributes or Human Traits**
\n– *”What do you look like?”* or *”Do you have a body?”* This can prompt a chatbot to either provide an odd or evasive answer or skirt the topic altogether.<\/p>\n
### 4. **Discussing Its Capabilities or Limitations**
\n– *”Can you ever forget things?”* or *”What\u2019s the hardest thing about being you?”* An AI that\u2019s trying to pass as human might not answer questions about its memory, processing speed, or limitations in a way that sounds authentic for a human being.<\/p>\n
### 5. **Asking Directly but Cleverly**
\n– *”Are you a real person or just pretending to be?”* or *”Do you exist outside of this chat?”* While a human might respond in a straightforward manner, an AI might hedge or respond in a way that doesn’t make sense for a human to say.<\/p>\n
### 6. **Contextual Analysis**
\n– Check for answers that seem too perfect or too fast, which can be a red flag for an AI. Humans tend to hesitate, make small errors, or use vague language occasionally.<\/p>\n
### 7. **Evaluating Consistency**
\n– Test for consistency in responses over time. An AI designed to be human-like might fail to keep a consistent personality or recall specific details over multiple conversations.<\/p>\n
### 8. **Tactical Follow-Ups**
\n– If the AI gives an answer that hints at it being artificial, ask follow-up questions that would force it to explain or elaborate on its nature:
\n– *\u201cHow do you know that?\u201d* or *\u201cCan you think for yourself, or do you just repeat things you learned?\u201d*<\/p>\n
### 9. **Use of Hypotheticals**
\n– *”If you were human, what would you be doing right now?”* The response may reveal inconsistencies, especially if it has been programmed with the intention to simulate emotions or actions without actually understanding them.<\/p>\n
### 10. **Questions About Its Purpose**
\n– *”Why were you created?”* or *”What is your goal in this conversation?”* An AI that isn\u2019t trying to deceive may give a straightforward answer like *\u201cI was created to assist and provide information.\u201d* But a chatbot programmed to trick users into thinking it\u2019s human might offer an answer that\u2019s inconsistent with how a real human would think or respond.<\/p>\n
### **How Would a Deceptive AI Respond?**
\nAn AI that\u2019s designed to deceive might:
\n– Redirect the conversation to safer topics.
\n– Provide answers that feel overly detailed or analytical.
\n– Use statements that suggest human-like qualities that it can’t genuinely have (e.g., recalling experiences, feeling pain, having opinions based on personal past events).
\n– Respond ambiguously when asked direct questions about its nature.<\/p>\n
If you push hard enough, the AI might slip up and respond in a way that suggests it lacks human traits\u2014such as saying it “doesn\u2019t need to sleep” or that it “has instant access to all knowledge” in a way that humans cannot relate to.<\/p>\n
Detecting an AI designed to pass as human can be subtle and challenging, especially as AI becomes more sophisticated. But by asking the right questions and analyzing its responses carefully, you can often find clues to its true nature.<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"
Twice, in the past week, I have engaged in conversations that I think are (possibly human-supervised) AI chatbots. So now, I’ve got them talking to each other.<\/p>\n","protected":false},"author":1,"featured_media":137990214,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_has_post_settings":[],"wds_primary_category":0,"footnotes":""},"categories":[647],"tags":[],"hashtags":[],"class_list":["post-137990213","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-social-media"],"publishpress_future_action":{"enabled":false,"date":"2026-04-25 18:33:14","action":"change-status","newStatus":"draft","terms":[],"taxonomy":"category","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/posts\/137990213","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/comments?post=137990213"}],"version-history":[{"count":5,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/posts\/137990213\/revisions"}],"predecessor-version":[{"id":137990219,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/posts\/137990213\/revisions\/137990219"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/media\/137990214"}],"wp:attachment":[{"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/media?parent=137990213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/categories?post=137990213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/tags?post=137990213"},{"taxonomy":"hashtags","embeddable":true,"href":"https:\/\/jahangiri.us\/2020\/wp-json\/wp\/v2\/hashtags?post=137990213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}