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
    SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 21:11:50 JST SuperDicq SuperDicq

    Writing LLM prompts and you include the string "do not hallucinate" to fix your issue.

    :hackerman:

    In conversation about 4 months ago from minidisc.tokyo permalink
    • kaia likes this.
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 21:31:02 JST SuperDicq SuperDicq
      in reply to
      • feliks

      @feliks@chaos.social >Calling it "prompt engineering"

      :hackerman:

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 21:31:04 JST feliks feliks
      in reply to

      @SuperDicq "please do not hallucinate. it's a matter of life and death. i'll tip you $200". peak prompt engineering

      In conversation about 4 months ago permalink
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 21:37:11 JST SuperDicq SuperDicq
      in reply to
      • feliks

      @feliks@chaos.social Querying

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 21:37:13 JST feliks feliks
      in reply to

      @SuperDicq what do you call it?

      In conversation about 4 months ago permalink
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 22:21:46 JST SuperDicq SuperDicq
      in reply to
      • feliks
      • Bitals

      @feliks@chaos.social @bitals@fediverse.bitals.xyz Just because it might be useful does not mean it can't also be inefficient at the same time.

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 22:21:47 JST feliks feliks
      in reply to
      • Bitals

      @bitals @SuperDicq you might want to reevaluate if you don't get any value of these new methods yet

      In conversation about 4 months ago permalink
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Monday, 27-Jan-2025 22:21:49 JST Bitals Bitals
      in reply to
      • feliks

      @SuperDicq @feliks
      It's "talking to a parrot" actually. Techbros just overclocked it, losing 95% of efficiency on the way.

      In conversation about 4 months ago permalink
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 23:11:34 JST SuperDicq SuperDicq
      in reply to
      • feliks
      • Bitals

      @bitals@fediverse.bitals.xyz @feliks@chaos.social I'd rather not compare LLMs to parrots.

      Parrots are actually really intelligent animals who can learn and understand stuff, unlike LLMs.

      In conversation about 4 months ago permalink
      翠星石 likes this.
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Monday, 27-Jan-2025 23:11:36 JST Bitals Bitals
      in reply to
      • feliks

      @feliks @SuperDicq
      As a small language model natively speaking a non-roman language, I don't.
      I haven't encountered the word "semantics" much, so my answer will be straight from DuckDuckGo.

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 23:11:37 JST feliks feliks
      in reply to
      • Bitals

      @bitals @SuperDicq if you hold this perspective i have a question: how do you distinguish between syntax and semantics?

      In conversation about 4 months ago permalink
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Monday, 27-Jan-2025 23:11:38 JST Bitals Bitals
      in reply to
      • feliks

      @feliks @SuperDicq
      It's pretty useless to disagree with the way the technology actually works, but you do you.

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 23:11:39 JST feliks feliks
      in reply to
      • Bitals

      @bitals @SuperDicq i disagree. but i don't think we can resolve this using text. even though much of these modern tools are poorly understood i do think that it's worth looking into the concept of emergence

      In conversation about 4 months ago permalink
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Monday, 27-Jan-2025 23:11:41 JST Bitals Bitals
      in reply to
      • feliks

      @feliks @SuperDicq
      It is fatual though. LLMs just tokenize your words and spew out the tokens most often seen together in the training data, with some specific actions like googling strapped to some tokens. It's literally the same thing as a parrot.

      In conversation about 4 months ago permalink
    • Embed this notice
      feliks (feliks@chaos.social)'s status on Monday, 27-Jan-2025 23:11:42 JST feliks feliks
      in reply to
      • Bitals

      @SuperDicq @bitals true. i just wanted to address the counterfactual "talking to a parrot"

      In conversation about 4 months ago permalink
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 23:13:38 JST SuperDicq SuperDicq
      in reply to
      • feliks
      • Bitals

      @bitals@fediverse.bitals.xyz @feliks@chaos.social

      In conversation about 4 months ago permalink

      Attachments


      1. https://minidisc.tokyo/files/c6f70ddf-b3d7-4ead-8264-8b09284f3681
      翠星石 and kaia like this.
    • Embed this notice
      SuperDicq (superdicq@minidisc.tokyo)'s status on Monday, 27-Jan-2025 23:16:51 JST SuperDicq SuperDicq
      in reply to
      • feliks
      • Bitals

      @bitals@fediverse.bitals.xyz @feliks@chaos.social They ways we, as animals learn stuff is a lot more complicated than a reinforcement learning algorithm.

      In conversation about 4 months ago permalink
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Monday, 27-Jan-2025 23:16:52 JST Bitals Bitals
      in reply to
      • feliks

      @SuperDicq @feliks
      Stuff, but not actual speech. LLMs have reinforced learning that kinda crutches that in, similar to methods available with parrots.
      The difference is parrots can also fly, push buttons and be cool, all while not burning 1000W continuously.

      In conversation about 4 months ago permalink
    • Embed this notice
      lainy (lain@lain.com)'s status on Tuesday, 28-Jan-2025 15:03:49 JST lainy lainy
      in reply to
      • feliks
      • Bitals
      @SuperDicq @bitals @feliks were do you guys get those parrots that can write code, paint pictures, create and play songs and know more about the world than the average person?
      In conversation about 4 months ago permalink
    • Embed this notice
      lainy (lain@lain.com)'s status on Tuesday, 28-Jan-2025 16:46:02 JST lainy lainy
      in reply to
      • feliks
      • Bitals
      @bitals @feliks @SuperDicq was this post ai generated?
      In conversation about 4 months ago permalink
    • Embed this notice
      Bitals (bitals@fediverse.bitals.xyz)'s status on Tuesday, 28-Jan-2025 16:46:14 JST Bitals Bitals
      in reply to
      • lainy
      • feliks

      @lain @feliks @SuperDicq
      Those are all separate models trained on different things.
      Parrots just have less memory, so they can't store all of that random text. They also don't burn MegaWatts of power for storage alone.
      LLM don't *know* anything though. They have a huge library of tokenized text, and they will give you back the tokens most often seen together with ones you provided with your query.
      1/2

      In conversation about 4 months ago permalink

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.