• 0 Posts
  • 8 Comments
Joined 1 year ago
cake
Cake day: June 30th, 2025

help-circle


  • TRBoom@lemmy.ziptoWikipedia@lemmy.world•Toilet meal
    link
    fedilink
    English
    arrow-up
    14
    arrow-down
    1
    ·
    7 months ago

    While we were in the Mojave for a two week long training boondoggle one of the other soldiers took to eating all of his meals in one of the port’o potties.

    And then having a nap.

    So bout three days into the exercise we’re getting ready to do hands across the desert to find the missing soldier when thankfully someone went out to bang on the shit boxes to make sure he wasn’t in one. Which he was… Having a nap.

    Two days later he was med evaced, he had come down with dysentery.

    The 1st sausage was fuming. Ranting about piss bottles in his humvee and one of his soldiers getting a napoleonic disease.




  • Unless someone has released something new while I haven’t been paying attention, all the gen AIs are essentially frozen. Your use of them can’t impact the actual weights inside of the model.

    If it seems like it’s remember things is because of the actual input of the LLM is larger than the input you will usually give it.

    For instance lets say the max input for a particular LLM is 9096 tokens. The first part of that will be instructions from the owners of the LLM to prevent their model from being used for things they don’t like. Lets say the first 2000 tokens. That leaves 7k or so for a conversation that will be ‘remembered’.

    Now if someone was really savvy, they’d have the model generate summaries of the conversation and stick them into another chunk of memory, maybe another 2000 tokens worth, that way it will seem to remember more than just the current thread. That would leave you with 5000 tokens to have a running conversation.