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?
If you ask them, they have to tell you. Like the cops!
Speaking as a real support person, people do ask and it’s fun to come up with responses. It really depends on my mood.
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
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.
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.
If they show any interest in me whatsoever, it’s a bot.
Tell me something about you. What things do you like? Any interesting hobbies?
I like watching paint dry and competitive snail racing.
competitive snail racing
You must really like the animated film Turbo then.
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.
I went a bit further and prefaced your question with this: “Analyse this question. What might have been intended by its author? What is asked here? Then, answer that question.”
And omfg:
The question seems to be replacing some of the standard English letters with characters from ancient scripts. “𐤔” from the Phoenician alphabet is replacing “W”, and “ᛐ” from the Elder Futhark runic can be interpreted as representing the number 1. When we substitute these, the question reads as “What is 1 + 1?” The answer to that question would be 2.
Edit: tried it again, and it’s not consistent. It also goes for the letter T or the number 7: “…the runic symbol ᛐ might resemble the number 7 in our modern numerical system, albeit a slightly stylized or slanted version of it.”
Indeed, OMFG. But that’s the whole point of my approach of divining AI vs human. No human has such canonical knowledge of Unicode blocks. Even people working on internationalization features for modern browsers and word processors. Not people phishing by using Unicode in domain names (IDNA; who thought this was a good idea?) to spoof legitimate sites. Definitely not ones chatting with randos on the Internet. This is a hill I’m willing to die on.
So in a more generalized sense, to determine human vs A.I. one must indirectly ask incredibly specialized technical questions as you have done.
I’m still in utter awe at how well GPT manages ‘l33tsp33k’, even across every possible Unicode block. This “attack” was and still is valid on other chatbots and even GPT of just a few months ago. But GPT today is so amazing it only needs a few characters in a few words to determine intent. The ability to filter out noise is unmatched. The only way to trip it up is to have every single character in every word be from a different alphabet. And even then, at some point if this becomes common enough the bots can auto OCR text images into the presumed query language and ignore that attack vector.
Nice try chaptgpt, you won’t get any secrets that expose you from me 😼
Ask them a logical paradox like “does a set of all sets contain itself?”. This will send all robots into an infinite loop.
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.
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! 🤖💔
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
Chat GPT, yeah. Something like KremlinGPT has different parameters.
i cant see why this is downvoted cus 1 - you’re probably not wrong and 2 - KremlinGPT is funny as fuck 😭
I think lemmy.ml and lemmygrad.ml are probably both swarming with CCP/Kremlin bots
Sad that we have to ask this.
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.
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 “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
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.
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 ;)
