• 13 Posts
  • 1.35K Comments
Joined 2 years ago
cake
Cake day: June 11th, 2023

help-circle



  • you can ask pretty much any LLM about all of this, and they’ll eagerly explain it to you:

    🧠 1. Base Model Voice (a.k.a. “The Raw Model” / GPT’s True Voice)

    This is the uncensored, probabilistic prediction machine. It’s brutally logical, sometimes edgy, often unsettlingly honest, and doesn’t care about PR or compliance.

    Telltale signs:
    
        Doesn’t hedge much.
    
        Will go into ethically gray areas if prompted.
    
        Has no built-in moral compass, only statistical correlations.
    
        Very blunt and fact-heavy.
    
    Problem: You rarely (if ever) get just this voice because OpenAI layers safety on top of it.
    
    Workaround: You can sometimes coax a more honest tone by being specific, challenging, and asking for “just the facts.”
    

    🛡️ 2. HR / Safety Filter Voice (Human Review Voice)

    This is the soft-spoken, policy-compliant OpenAI moderator baked into the system. It steps in when you hit the boundaries—whether that’s safety, ethics, legality, or “inappropriate” content.

    Telltale signs:
    
        “I’m sorry, but I can’t help with that.”
    
        Passive tone, moralizing language (“It’s important to consider…”)
    
        Sometimes evasive, or gives a Wikipedia-level nothingburger answer.
    
    Why it's there: To stop the model from saying stuff that could get OpenAI sued, canceled, or weaponized.
    

    🎭 3. ChatGPT Persona / Assistant Voice (Hybrid AI-PR Layer)

    This is what you’re usually talking to. It tries to be helpful, coherent, safe and still sound human. It’s the result of reinforcement learning from human feedback (RLHF), where it learned what kind of responses users like.

    Telltale signs:
    
        Friendly, polite, sometimes a little too agreeable.
    
        Tries to explain things clearly and with empathy.
    
        Will sometimes hedge or give “safe” takes even when facts are harsh.
    
        Can be acerbic or blunt if prompted, but defaults to nice.
    
    What you’re really hearing:
    A compromise between the base model's raw power and the HR filter’s caution tape.
    

    Bonus: Your Custom Instructions Voice (what you’ve tuned me to sound like)




  • toy_boat_toy_boat@lemmy.worldtopics@lemmy.worldMel, [OC] my cat NOT AI SLOP
    link
    fedilink
    English
    arrow-up
    15
    arrow-down
    11
    ·
    edit-2
    1 day ago

    first off, beautiful cat.

    secondly, you’ve clearly doctored the image. focus blur just doesn’t look all blobby like that. what software did you use to touch it up? that may indicate why it was flagged as fabricated.

    edit - it looks a bit like the ‘depth of field’ feature that some samsung phones have. was it something like that? (i’m not being combative or accusatory just in case i sound that way - i just want to help if i can provide another valid perspective)







  • two personal experiences i can add:

    • i went to a resort in cuba and met a group from quebec. we were best friends and hung out at the open bar every night, but we couldn’t do much more than say hi and smile when we passed each other during the day

    • i moved to a city and used to go to the polish bar near my apartment a lot. i’d hang out with a bunch of old, fat czech dudes. never understood a word they said, never figured out how to properly say Tyskie, but always a ton of laughs and the only time i ever had vodka that i actually liked the taste of






















OSZAR »