Achieving AI-style reasoning without an LLM

(fleetingswallow.com)

35 points | by edwardchalk 2 hours ago

8 comments

  • vintagedave 7 minutes ago
    > A large language model is trained to predict the next word of a piece of text. … simply asking a model to “think step by step” makes its answers better.

    I thought both these statements were no longer held to be broadly true? At least in big lab or frontier models.

    • nayroclade 1 minute ago
      Next token prediction is still how pre-training works, but that's a relatively small part of the whole training run nowadays. Most of the time is spent in post-training reinforcement learning scenarios, where models are scored based on an evaluation of their ability to complete a task, not whether any specific token correctly predicts a known next token.

      Generally, anyone talking about next token prediction being some limiting factor of LLM capability is a good reason to ignore them, as they haven't updated their understanding of LLMs since 2023 or so.

    • asdfsa32 4 minutes ago
      Only the meaning of "next" and "word" as well as "next word" has become more complicated, otherwise it still holds true as a general mechanism.
  • iterance 25 minutes ago
    The associated paper is (I will say generously) not forthcoming: https://zenodo.org/records/23526702

    I can also find no working model. I expect this may be disregarded for now.

  • jstanley 38 minutes ago
    I can't see where you can try this out, so at the moment it's a lot of claims and no real evidence. Also the text feels like it was written by an LLM.

    If it's really such a small model why not provide a web interface where we can test it for ourselves?

    This feels like high risk of being crackpottery.

  • 8474_s 15 minutes ago
    > without a LLM https://github.com/pcoz/decisionator

    2. Obtain an OpenAI API Key

        Sign up at OpenAI
        Create an API key
    • jstanley 13 minutes ago
      I'm pretty sure that's a different project
      • 8474_s 8 minutes ago
        Its the only repo by the author(Edward Chalk) that focuses on decision making models? Its his github account linked from the front page.
  • kangalioo 1 hour ago
    Never seen that one before:

    "Insufficient Storage

    The method could not be performed on the resource because the server is unable to store the representation needed to successfully complete the request. There is insufficient free space left in your storage allocation.

    Additionally, a 507 Insufficient Storage error was encountered while trying to use an ErrorDocument to handle the request."

  • cubefox 4 minutes ago
    This might have been written by someone suffering from AI psychosis.
  • suddenlybananas 36 minutes ago
    It's really a nitpick but putting a big, obvious AI generated slop photo at the top of your post is a signal for bad quality content. I would recommend to avoid doing it.
    • tarkin2 10 minutes ago
      And using AI's favourite phrase, a deep dive, is also offputting.

      (I mean, is he grading the dive?)