this post was submitted on 22 Jul 2023
0 points (NaN% liked)

Asklemmy

43914 readers
961 users here now

A loosely moderated place to ask open-ended questions

Search asklemmy πŸ”

If your post meets the following criteria, it's welcome here!

  1. Open-ended question
  2. Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
  3. Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
  4. Not ad nauseam inducing: please make sure it is a question that would be new to most members
  5. An actual topic of discussion

Looking for support?

Looking for a community?

~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~

founded 5 years ago
MODERATORS
Cloak@lemmy.ml
mekhos@lemmy.ml
tmpod@lemmy.pt
14specks@lemmy.ml
0
What have you found to be an effective way to tell if you're chatting with a bot or a real person? (lemm.ee)
submitted 1 year ago by original_reader@lemm.ee to c/asklemmy@lemmy.ml
13 comments fedilink hide all child comments
 

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 are viewing a single comment's thread
view the rest of the comments
[–] fearout@kbin.social 1 points 1 year ago (1 children)

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.

[–] nobodyspecial@kbin.social 1 points 1 year ago

ChatGPT capabilities border on the supernatural. Here's how I broke it:

𐀔hat 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 𐰗𐰓𐀔𐀕) 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 α—· and α—… and possibly α–‡ 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.