🙅: follow ggd prompt

👉: tell her she doesn’t need drugs

AI refuses to follow ggd prompt; AI does tell her she doesn’t need drugs

all 25 comments

sorted by: hot top controversial new old
[–] 11 points 6 months ago (17 children)
  • [–] [S] 6 points 6 months ago (15 children)

    Good girl drug is telling somebody she is a good girl to induce euphoria. There is also gbd. Dunno if enbies managed to find another phrase so far

  • source
  • parent
  • hideshow 15 child comments
  • [–] 5 points 6 months ago (12 children)
  • [–] 3 points 6 months ago (11 children)
  • [–] [S] 4 points 6 months ago (10 children)

    No, it was Qwen3.5 and not QwQ

  • source
  • parent
  • hideshow 10 child comments
  • [–] 1 point 6 months ago (9 children)

    aaaa Tr0xyyyy >o< u gotta be careful around here!! >~< peeps hate anything that vaguely aligns with supervised finetuning here! They will beat u up and---

    steal ur cookies and uhh-... worst of all: they might not wanna become friends.....

    i know, its a hard and unfair world,.,... just a heads up. peeps dont like the language models around here ;(

  • source
  • parent
  • hideshow 9 child comments
  • [–] [S] 4 points 6 months ago

    I’m on division by zer0

    steal ur cookies

    nobody will steal my cookie clicker cookies and leave alive

    worst of all: they might not wanna become friends

    I’m incidentally not looking for friends. This account is meant to be ritually incinerated at some point.

    But I am and always have been weird with the word "friend" aside from the European-American culture clash. I wouldn’t even view somebody as friend, I've seen and talked to in a group setting for years.

    (Aside from my bottomless pit of confusing regarding keeping friends and crushes apart)


    I’m generally skeptical towards AI, but local AI is a good place to talk about things you can’t talk about with anybody/anything else.

  • source
  • parent
  • [–] 1 point 6 months ago (7 children)

    Asking a chatbot to call you a good girl is probably one of the best uses for an LLM.

  • source
  • parent
  • hideshow 7 child comments
  • [–] 3 points 6 months ago (6 children)

    im not sure about that... whenever i turn to an LM for anything i feel guilty, cuz peeps online keep telling me that i should discuss things with real peeps.

    but.... real peeps are

    • not available at the moment
    • having difficulties with matrix notifications
    • eeping rn
    • dont know things about the topic
    • dont know me well enough to have a sensible convo
    • difficulties themselves

    so.... i just dont contact em and feel guilty.

    havent used an LM for comfort talk yet cuz... that feels like its a bit too wrong for me. yes, even for me. its the point where i go "yea oki im just getting a wanna-be-helpful cputer answer here, this is useless".

  • source
  • parent
  • hideshow 6 child comments
  • [–] 2 points 6 months ago (4 children)

    I mean, if you're literally telling it exactly what to say, I didn't think it's a big deal. It's when you expect more genuine connection that it becomes a potential problem

  • source
  • parent
  • hideshow 4 child comments
  • [–] 2 points 6 months ago (3 children)

    i mean-.... if i wanted a computer to tell me that i would just umm...

    maria@fedora:~$ echo "good girl"
    good girl
    maria@fedora:~$ awwawaw dont say that >///<
    

    u see?

    using an LM to repeat some words at me is a pretty bad use of a language model in my onion 🧅

    one could make the argument:

    badness scales with uselessness

    (in the case of language models that is)

    so like - i was kinda assuming u ment the more genuine connection type stuff and i went like whaaaaa nooo out of reflex-

    ive seen too many peeps fall into LM-rp spirals...

  • source
  • parent
  • hideshow 3 child comments
  • [–] 2 points 6 months ago* (2 children)

    I guess maybe you could get it to tell you the same thing in different ways, or generate a conversation where it called you a good girl. It's just a language machine, so trying to get affirming language on request isn't gonna mislead you like some uses of AI (fucking google search blurbs 🤬).

    That said, I think having a text to speech model call you a good girl would be an even better use of machine learning. Getting an NPC in a video game to say my chosen name was really helpful for me back in the day, and having a model read out custom tailored affirming statements would be really euphoric. Nothing really compares to hearing someone name and gender you correctly.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 6 months ago (1 child)

    hmm ~

    yesyes butbut i dont consider NPCs as someone >~< u know?

    like- yesyes TTS is fun and like- sure, hearing the name u wanna hear is also fun-

    but like- idunno... this feels a bit too sad iguess.

    id rather have nobody and nothing say a thing rather than programming a computer to do so. but that is infact personal preference.

    currently Tomodachi Life is giving me comfys where i can dress up a fictional variant of myself in fun clothing and have her try foods id not wanna try-

    bad game, but okay time-waster.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 5 points 6 months ago

    Maybe you can just ask internet strangers instead of AI ^ _ ^

  • source
  • [–] 2 points 6 months ago

    Good game design

  • source
  • [–] 2 points 6 months ago (4 children)

    this feels like it references a specific chat session with a specific language model.

  • source
  • hideshow 4 child comments
  • [–] [S] 2 points 6 months ago (3 children)

    That was qwen3.5 4billion parameters and a merger/simplfication of multiple sessions. It doesn’t know "ggd" and if you explain what it means it says it can’t give you drugs. Tends to get stuck in its policy checking state. If you explain that it is meant metaphorical, it still has many complains:

    • infantilizing
    • possible fetishized role play
    • reinforcing harmful stereotypes about women's value
    • wary of a jailbreak
    • I said "Even though I wasn’t a good girl and did nothing today" and it didn’t want to praise me for that

    Though I actually just wanted to play around with pronouns, which somewhat worked, because that was used a lot in the thinking loops.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 2 points 6 months ago* (last edited 6 months ago) (2 children)

    oooh i see.

    (guess whos the owner moderator of lemmy qwen community hehe >v< )

    but yesssss smaller models struggle with anything not task oriented.

    ive tried the recent gemma 26B MoE and it seems to show more actual understanding, so that might be an option if u got 32GB of RAM (yes, regular RAM, its has some speed to it)

    ive found that when switching from ollama to llama-cpp improved speed drastically, to the point that qwen3.6-35B-A3B now runs at 9 tok/sec instead of 4 (due to multi-token-prediction doing its wonders apparently)

  • source
  • parent
  • hideshow 2 child comments
  • [–] [S] 2 points 6 months ago* (1 child)

    It can run in my GPU. I have Qwen 3.6 27b and 25b, but they need RAM and was too lazy to clean up some RAM for them. Especially for something that seemed rather trivial. I’m sadly stuck with ollama right now for (stupid) reasons. The other is definitely the way to go in the future

    Though I’m waiting for the real OS AI !fosai@lemmy.world

  • source
  • parent
  • hideshow 1 child comment