

okay, that’s cool i guess? but who is “she” and why did shey say “twss”?
okay, that’s cool i guess? but who is “she” and why did shey say “twss”?
i don’t know what that stands for, so i just read it like you said it as a word. still works.
i just want to know why it’s in the oven
and yet you persist. why?
(sorry, this is totally a troll)
the illusion is STRONG. i just typed up two draft replies before i realized what actually you’re saying here.
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)
yeah, i didn’t even try to order that one haha
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
unless anyone involved has any issues with alcohol, i STRONGLY suggest picking up a couple bottles of wine. this is not a joke.
you’re absolutely right. they actually don’t know anything. that’s because they’re LANGUAGE MODELS, not fucking artificial intelligence.
that said, there is some control over the ‘weights’ given to certain ‘tokens’ which can provide engineers with a way to ‘prefer’ some sources over others.
i see what you mean, and i agree that “sweetened” laughter (adding some sfx to a studio audience) is much more bearable than the canned stuff. still, it’s funny that we had to be hand-held and told what parts were funny. didn’t think much of it at the time, but now it’s really annoying
my god, i can’t believe how much bad canned laughter we used to tolerate on television! now that it isn’t everywhere any more, it’s so easy to spot and so grating to hear. i wonder if there’s a way to cleanly remove it from these skits.
if LLMs were marketed as language assistance and productivity tools, that would be splendid. instead, they plug it into google and tell everyone it’s artificial intelligence. Now it just bullshits to everyone because they think they’re talking to a sentient fucking machine instead of 21st-century Clippy.
all that said, your post has a bit of an accusatory and judgemental tone to it - at least as i’m reading it. did i address your concern?
i mean, i even put a disclaimer at the bottom… :P
all good, glad you shared the real chemistry
when LLMs are used to replace actual intelligence, then yeah i hate them. they’re pretty funny sometimes, too. just like autocorrect.
okay, so i normally hate LLMs, but this is pretty funny.
here’s my joke: “you think he’ll share his breakup spotify playlist? i bet it has lots of evanescence on it”
here’s what it suggested instead: “You think he’ll drop his breakup playlist? Bet it’s just Grimes tracks and the sound of him refreshing Trump’s DMs.”
edit - LMAO
“Can’t wait for Elon’s breakup playlist. Probably just Grimes songs and audio clips of him begging Trump to like him again.”
deleted by creator
see? this is what i mean! there are whole oceans made of sodium and water! if you knew some basic chemistry, you’d at least know that… jeez!
(this is a joke. i feel compelled to state very clearly that this is a joke)
that’s cool! i assumed it had something to do with moisture