GNU social JP
  • FAQ
  • Login
GNU social JPは日本のGNU socialサーバーです。
Usage/ToS/admin/test/Pleroma FE
  • Public

    • Public
    • Network
    • Groups
    • Featured
    • Popular
    • People

You said: how many r's are there in strawberry ChatGPT said: There are two "r"s in the word "strawberry." You said: no there are 3 ChatGPT said: The word "strawberry" actually has two "r"s, not three. The letters are in these positions: "strawberry". If you have another word or context in mind, feel free to share! You said: The word you just showed my highlighted 3 "r"s! ChatGPT said: I see how that might have been confusing! I highlighted the same "r" twice within the "rr" sequence. Let me clarify: The word "strawberry" contains two distinct "r" letters: One "r" is in the fourth position: str**awberry The second "r" is part of the "rr" combination: strawberry So there are a total of two "r"s in the word "strawberry." Sorry for any confusion earlier! You said: No, Let me highlight it for you stRawbeRRy. There are 3 r's there ChatGPT said: I see what you’re pointing out, but the correct count still is two "r"s in the word "strawberry." Here's how it breaks down: The first "r" is in "strawberry." The second "r" is in the "rr" sequence: "strawberry." Even though "rr" has two "r"s together, it still counts as only two individual "r"s in the entire word. There are not three separate "r" letters; there are two. I hope this clears up any confusion!

Download link

https://social-coop-media.ams3.cdn.digitaloceanspaces.com/media_attachments/files/113/047/882/609/420/368/original/a2df794b7cfc0799.png

Notices where this attachment appears

  1. Embed this notice
    Scott Jenson (scottjenson@social.coop)'s status on Friday, 30-Aug-2024 08:29:08 JST Scott Jenson Scott Jenson

    This "how many Rs in Strawberry" mistake with chatGPT is going around. I just tried it here:
    https://chatgpt.com/c/0b62bdd5-b33c-45d0-b0ed-f1c780d3533d
    There appear to be a fews camps trying to spin this:
    * a trivial 'gotcha'
    * a warning on the limits of LLMs

    There is likely a bit of truth in both. It clearly shows LLMs mimic language but not thought. It was incapable of responding to my very clear rebuttals.

    There are going to be profound uses of this tech, but we must see it, and it's limitations, clearly.

    In conversation about 10 months ago from social.coop permalink
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.