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

Conversation

Notices

  1. Embed this notice
    Zach Weinersmith (zachweinersmith@mastodon.social)'s status on Saturday, 27-Jul-2024 23:37:53 JST Zach Weinersmith Zach Weinersmith

    Are there any LLMs yet that are able to kick questions over to a physics model? Like, it seems that at least for some questions, the way we get an answer isn't by thinking about what we've seen or learned or said before, but literally imagining the world. For kids, this seems to include things like finger counting for addition.

    In conversation about 10 months ago from mastodon.social permalink
    • Doughnut Lollipop 【記録係】:blobfoxgooglymlem: likes this.
    • Embed this notice
      Zach Weinersmith (zachweinersmith@mastodon.social)'s status on Saturday, 27-Jul-2024 23:57:58 JST Zach Weinersmith Zach Weinersmith
      in reply to

      Like, GPT-3 failed questions of the form "I'm in the basement and look at the sky. What do I see?" GPT-4 fixed this by having humans correct its mistakes. I imagine if I were a kid getting this question for the first time, especially in a place where there aren't typically basements, what I'd do is probably imagine being in a basement.

      In conversation about 10 months ago permalink
    • Embed this notice
      Zach Weinersmith (zachweinersmith@mastodon.social)'s status on Saturday, 27-Jul-2024 23:57:58 JST Zach Weinersmith Zach Weinersmith
      in reply to

      And the model I use could be fairly stupid. Just a sort of underground box. No need for deep physics or even an understanding of what the point of a basement is.

      In conversation about 10 months ago permalink
    • Embed this notice
      Jake Hildreth (acorn) :blacker_heart_outline: (horse@infosec.exchange)'s status on Saturday, 27-Jul-2024 23:57:58 JST Jake Hildreth (acorn) :blacker_heart_outline: Jake Hildreth (acorn) :blacker_heart_outline:
      in reply to

      @ZachWeinersmith From what I understand, LLMs maintain no model of the physical world of any sort, so they wouldn’t even be able to identify a question that needed to be referred to a physics model.

      In conversation about 10 months ago permalink
    • Embed this notice
      Jake Hildreth (acorn) :blacker_heart_outline: (horse@infosec.exchange)'s status on Saturday, 27-Jul-2024 23:59:20 JST Jake Hildreth (acorn) :blacker_heart_outline: Jake Hildreth (acorn) :blacker_heart_outline:
      in reply to

      @ZachWeinersmith I’m most relying on this episode of “Better Offline” for my comment: https://overcast.fm/+ABGz6_D9Lk8

      In conversation about 10 months ago permalink

      Attachments

      1. Domain not in remote thumbnail source whitelist: public.overcast-cdn.com
        The Academics That Think ChatGPT Is BS — Better Offline

Feeds

  • Activity Streams
  • RSS 2.0
  • Atom
  • 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.