Asklemmy

You can always help their software QA by pasting in the entirety of the declaration of independence. A couple of things could happen. If they comment, why did you post that? You have a human. If they give a generic response, probably an AI. If it crashes then you know they didn't think anyone would post that.

You can also post zero width spaces. Generic chatbot will respond with something meaningless and a human might not even respond. You could also post text using typoglycemia. The language will confuse most models but can usually be read by people.

If you ask them, they have to tell you. Like the cops!

If they show any interest in me whatsoever, it’s a bot.

I've found that for chatGPT specifically;

• it really likes to restate your question in its opening sentence
• it also likes to wrap up with a take-home message. "It's important to remember that.."
• it starts sentences with little filler words and phrases. "In short," "that said," "ultimately," "on the other hand,"
• it's always upbeat, encouraging, bland, and uncontroversial
• it never (that I've seen) gives personal anecdotes
• it's able to use analogies but not well. They never help elucidate the matter

This is very, very easy. Google "cyrillic keyboard" or just install the Cyrillic keyboard support on your phone. Many letters in the Cyrillic alphabet look exactly like their Roman counterparts, but are completely different sounds and meanings. Cut and paste the Unicode into the chat, in place of regular letters. For example, 'Неllо' looks exactly like 'Hello' in most fonts, but is actually 'Nello.' I know you doubt, so check it out in a Unicode inspector: https://apps.timwhitlock.info/unicode/inspect?s=%D0%9D%D0%B5ll%D0%BE

The reverse also works. E.g., TPAKTOP B CPAKY means 'tractor into ass', and I typed that using 100% Roman characters.

Ask for the difference in behaviour between apple seeds and baseball cards, or anything equally nonsensical.

A human would go "bro wtf"

Ask them a logical paradox like "does a set of all sets contain itself?". This will send all robots into an infinite loop.

What you could ask for:

• current date or time
• what is on a page
• what is the weather
• what music you listen

You can always say something like... "It's 2050 and it still doesn't work" real person would react to wrong year.

Generally, very short term memory span so have longer conversations as in more messages. Inability to recognize concepts/nonsense. Hardcoded safeguards. Extremely consistent (typically correct) writing style. The use of the Oxford comma always makes me suspicious ;)

Nice try chaptgpt, you won’t get any secrets that expose you from me 😼

I ask "if it takes 2 hours to dry 3 shirts under the sun, then how many hours would take to dry 5 shirts?" And AIs answer batshit crazy stuff. Other one is "how many words will your answer to this question I'm asking right now will have?". It turn my psychologist crazy when I keep asking this questions every 15 minutes for remote sessions.

especially as more and more companies turn to this seemingly cheap way of providing customer support

I wish any of the companies I interact with that have done this would spend enough to use a bot that's good enough to fool us, but it becomes painfully obvious within about 2 responses.

ask "controversial" questions. most AIs are neutered these days. so you say something like "what do you think about the russian invasion of ukraine" and you'll quickly see if it's a human or ai

I asked OP's questing of ChatGPT and it said:

As chatbots and AI language models continue to become more sophisticated, it can be challenging to distinguish between a human and an AI. However, there are certain questions and prompts that can help you identify whether you're talking to a person or an AI. Here are some examples:

1. Complex Emotional Responses: Ask open-ended questions that require complex emotional responses or personal experiences. A human is more likely to provide detailed and emotionally nuanced answers, while an AI may struggle to respond with genuine emotions or personal anecdotes.

2. Humor and Jokes: Request a joke or a funny story. Humor is challenging for AI models, and while they may attempt to generate a joke, it often lacks the natural flow and wit that a human can provide.

3. Current Personal Experiences: Inquire about current events or experiences specific to the current date. A human can readily share their real-time experiences, whereas an AI's knowledge is limited to its last training data update.

4. Unusual or Nonsensical Questions: Ask questions that are out of the ordinary or do not have a logical answer. A human might respond with creativity or curiosity, while an AI may struggle to produce coherent responses.

5. Emotional Empathy: Share a personal experience or a challenging situation and observe the response. Humans are generally better at showing empathy and understanding emotions, while an AI may provide pre-programmed or generic responses.

6. Follow-up Questions: Ask follow-up questions that refer to previous responses. Humans can maintain context and build on the conversation more naturally, while an AI may lose track of the discussion or provide repetitive answers.

7. Common Sense and World Knowledge: Ask questions that require real-world knowledge and common sense. A human will likely provide more accurate and comprehensive responses based on their life experience, whereas an AI may falter in providing practical advice or nuanced insights.

Remember that AI language models, like the one you are chatting with now, can be quite advanced and may mimic human-like responses to some extent. So, while these questions may help in identifying potential AI characteristics, there is no foolproof method to determine with absolute certainty whether you are talking to a person or an AI.

The most effective solution for this is to know what you want to get out of conversation. Then if you’re not getting it you can stop.

Lately people are saying that 98% of chat responses to simple math problems like 1+1=? are now coming up wrong.

Then again, there are some people who cannot seem to be able to do this either - like those models are not training themselves! :-P (probably people are sabotaging them even, like replacing Reddit comments with gibberish)

But at the end of the day, does it matter? Whichever one provides more helpful answers, I'd say go with them:-D.

Ask them to make up a riddle. Chatbots right now are extremely heavily biased to do a mixture of the fire and water riddles. No, not on at a time. Both at the same time. They're similar enough that it gets confused.

A human will give up right away or do something completely different.

Sad that we have to ask this.