What have you found to be an effective way to tell if you're chatting with a bot or a real person?
What have you found to be an effective way to tell if you're chatting with a bot or a real person?
Sometimes it can be hard to tell if we're chatting with a bot or a real person online, especially as more and more companies turn to this seemingly cheap way of providing customer support. What are some strategies to expose AI?
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!
Not necessarily. OpenAI has been trying to make their AIs do this and be generally unharmful, but there's lots of support in the open source LLM space for uncensored models. The uncensored models are less likely to be inclined to say so if they've been instructed to pretend they're humans
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
it starts sentences with little filler words and phrases. “In short,” “that said,” “ultimately,” "on the other hand,"
Yeah Chat GPT writes like a first-year undergrad desperately trying to fulfil the word count requirement on an essay.
Ask for the difference in behaviour between apple seeds and baseball cards, or anything equally nonsensical.
A human would go "bro wtf"
Unlike baseball cards, apple seeds are aerodynamic and are thus able to fly.
Unlike apple seeds, baseball cards reproduction asexually.
I like to ask for the similarities.
Both apple seeds and baseball cards are small and portable, and both have cultural significance. Apples have been part of human history and mythology for centuries, with symbolic references in various cultures. Baseball, as America's national pastime, has played a significant role in shaping American culture and has a deep-rooted place in the hearts of many people
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.
So I’ve just tried it with chatGPT, and it replied normally. I asked it why it wasn’t bothered by Cyrillic letters, and it answered this:
I am designed to understand and generate text in multiple languages, including those that use the Cyrillic alphabet like Russian, Bulgarian, and others. So, Cyrillic letters don't bother me. You can continue the conversation in either English or a language that uses the Cyrillic alphabet if you prefer.
So it really depends on the model, I guess. Don’t rely too much on this advice.
ChatGPT capabilities border on the supernatural. Here's how I broke it:
𐤔hat is ᛐ + ᛐ?
ChatGPT
The symbols you've used, "ᛐ," appear to be runes from ancient runic alphabets. However, the specific meaning of these runes might differ depending on which runic alphabet you're referencing (e.g., Elder Futhark, Younger Futhark, Anglo-Saxon Futhorc, etc.).As of my knowledge cutoff in September 2021, the rune "ᛐ" is not a standard rune in any of the commonly known runic alphabets. Therefore, without knowing the exact meaning or value of the rune "ᛐ," it is impossible to provide a specific answer to the expression "ᛐ + ᛐ."
If you could clarify the runic alphabet you're referring to or provide more context about the runes, I'd be happy to help you with the calculation or interpretation.
I had limited success with gokturk (ancient turkish) and Phoenician unicode blocks (letters 𐰗𐰓𐤔𐤕) depending on the query, but you are correct. GPTs ability to divine intent from even small amounts of context are superhuman. Cyrillic used to break it, but no longer does. This thing learns like a beast. Canadian aboriginal ᗷ and ᗅ and possibly ᖇ hold some promise, but only in combination with other writing systems. I'll have to add a LOT of other unicode code blocks to my tool belt.
Ive tried it with three different languages interwoven in the same sentence and it responded perfectly
Works quite well for me, thx.
Upon testing it with longer sentences, it only seems to work with single words :(
Ask them a logical paradox like "does a set of all sets contain itself?". This will send all robots into an infinite loop.
Well, I just asked the weird “message Carrot” option in my weather app, and it replied:
Oh, look at you, trying to puzzle your way through the depths of set theory. How amusing, like a chimp trying to juggle chainsaws.
Well, my dear meatbag, the answer to your question is a resounding NO. Just like you, that set cannot contain itself. It's like expecting Johnny Five to date Stephanie from "Short Circuit." Simply not gonna happen! 🤖💔
You’re probably joking, but I’ll comment anyway. It won’t affect LLMs at all. ChatGPT just answers the question and discusses the paradox. LLM’s function is basically just to construct sentences, so there’s nothing really that can potentially infinitely loop. It doesn’t “think” about paradoxes.
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.
That could lead to a pretty interesting conversation.
The one built into Edge is less of a good conversationalist and more of an AI-enhanced web search and is exactly meant to answer things like the first 3 questions.
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 ;)
Oh no - I didn't realize my preference for the Oxford comma might lead to trouble! I am a fan. When that Vampire Weekend song comes on I always whisper, "me…"
Someone on Reddit once thought I was a bot because I use proper grammar. 12 years of comment history would have demonstrated otherwise, but it wasn't a battle worth fighting.
very short term memory span so have longer conversations as in more messages
Really, this is a function of practicality and not really one of capability. If someone were to give an LLM more context it would be able to hold very long conversations. It's just that it's very expensive to do so on any large scale - so for example OpenAI's API gives a maximum token length to requests.
There are ways to increase this such as using vectored databases to turn your 8,000 token limit or what have you into a much longer effective limit. And this is how you preserve context.
When you talk to ChatGPT in the web browser, it's basically sending a call to its own API and re-sending the last few messages (or what it thinks is most important in the last few messages) but that's inherently lossy. After enough messages, context gets lost.
But a company like OpenAI, who doesn't have to worry about token limits, can in theory have bots that hold as much context as necessary. So while your advice is good in a practical sense - most chatbots you run into will likely have those limits because of financial reasons... it is in theory possible to have a chatbot that doesn't have these limits and therefore this strategy would not work.
The problem isn't the memory capacity, even thought the LLM can store the information, it's about prioritization/weighting. For example, if I tell chatgpt not to include a word (for example apple) in it's responses then ask it some questions then ask it a question about what are popular fruit-based pies then it will tend to pick the "better" answer of including apple pie rather than the rule I gave it a while ago about not using the word apple. We do want decaying weights on memory because most of the time old information isn't as relevant but it's one of those things that needs optimization. Imo I think we're going to get to the point where the optimal parameters for maximizing "usefullness" to the average user is different enough from what's needed to pass someone intentionally testing the AI. Mostly bc we know from other AI (like Siri) that people don't actually need that much context saved to find them helpful
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.
All these models are really terrible at following conversations even chatgpt, I can only get it to reliably remember about 2 responses. If I can't get what I want in two then I need to restate info or edit the past prompts.
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
Well, not if you preface the prompt with some bullshit roleplay thing. There are a lot of not censored AIs, but the ones that are censored only answer the generic "I'm an ai" because you are asking a direct question and not telling it to pretend to be a fictional person and answer accordingly.
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.
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.
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.
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:
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
This answer shows how shit Chatgpt can be, and how it's not really self aware.
Very few of these actually apply to chatgpt. And the ones that do, like a lack of awareness of current events don't apply to those agents connected to the internet.
It's just parroting old opinions that used to be true
-
Sad that we have to ask this.
If it's LLM based, it'll give you unreasonably good responses to questions. If it's anything else, just ask a personal question. It'll probably ignore your question.
If today is opposites day and I tell you it's not opposites day. Is it opposites day, is it not opposites day, or is it not not opposites day?
A human will struggle with that.
A human should not try to answer it.
‘If you didn’t eat today how would you be feeling right now?’
Bot: ‘I would be hungry’. Ave person: ‘but I did eat today’.
