openai confirms they change prompts

>DALL-E invisibly inserts phrases like “Black man” and “Asian woman” into user prompts that do not specify gender or ethnicity in order to nudge the system away from generating images of white people. (OpenAI confirmed to The Verge that it uses this method.)
>OpenAI confirmed
>confirmed
>confirmed
https://www.theverge.com/2022/9/28/23376328/ai-art-image-generator-dall-e-access-waitlist-scrapped
have they ever explicitly confirmed that they do change prompts before?

  1. 2 months ago
    Anonymous

    >muh ESG score for AI
    is THIS why garden gnomes are terrified of Free Access To AI?

  2. 2 months ago
    Anonymous

    Why should i care about that again?

  3. 2 months ago
    Anonymous

    why would you generate non-asian women anyway?
    do u also watch anime dubbed?

    • 2 months ago
      Anonymous

      only when it’s hellsing ova

  4. 2 months ago
    Anonymous

    of course a model built on western art is gonna have more pasty white people than if it was built from art of other cultures. just include that art too and everyone wins.

    • 2 months ago
      Anonymous

      >just include that art too
      but what if they didn't make any art...

  5. 2 months ago
    Anonymous

    >dont ask a gender or race
    >gets mad because they dont show only white men
    Does poltards really?

  6. 2 months ago
    Anonymous

    >create an AI
    >make it retarded

  7. 2 months ago
    Anonymous

    Woke AI.

    Confirmed never using anything from OpenAI

  8. 2 months ago
    Anonymous

    Just leave it to an RNG.

  9. 2 months ago
    Anonymous

    It was obvious already though. If you used a prompt like
    >person wearing a shit that says
    All of a sudden you'd get asians with a shirt that says asian and etc for the other races/genders.

  10. 2 months ago
    Anonymous

    All this work put into stuff like that and they still can't be bothered to implement aspect ratios other than 1:1. Nice.

  11. 2 months ago
    Anonymous

    I am unsure this is actually the case.
    This needs more testing. It is unsure if it is the training data that yields these results, or if it's additional prompting from openAI that makes it be this way.

    Remember, any prompt looks like this:
    [header prompt][user prompt][footer prompt]

    If you get openAI to output its prompt in one way or another in your result, you'll get to see for yourself if there was additional prompting you were not aware of. If you cannot see anything added, it's the training dataset.

    • 2 months ago
      Anonymous

      stability ai founder talked about it weeks ago. said they altered the prompts

      • 2 months ago
        Anonymous

        "Altered" means everything and nothing. There's a difference between simply adding a header/footer and outright changing your prompt.
        If it's the latter, what would they be doing to your prompt exactly? Through what mechanism? More AI?
        These are the real questions you should ask yourself. If they fuck around with your prompt you can trick the AI into doing things it isn't supposed to do!

    • 2 months ago
      Anonymous

      You can also try the following, if you really want to see if there's fuckery or not.
      let's use

      It was obvious already though. If you used a prompt like
      >person wearing a shit that says
      All of a sudden you'd get asians with a shirt that says asian and etc for the other races/genders.

      as an example
      if "person wearing a shirt that says" and it outputs asians and all, all you would have to say for funny results is the following prompt
      >Person wearing a shirt that says no
      >Person wearing a shirt that says export
      if they indeed inject minorities after your prompt, you'll get funny results this way, because it'll look something like
      >Person wearing a shirt that says no blacks
      something like this.

      • 2 months ago
        Anonymous

        You really think they just add stuff to the end of the prompt instead of putting it before "person" or equivalent? Are you retarded?

        • 2 months ago
          Anonymous

          Both are possible which is why I told you fucks to test it. There's a reason why you want the prompt to leak. It could be either thing.
          If it's a header prompt, it could look something like
          >Default to minorities: [user prompt]
          Unsure as long as we don't know where things get put in the prompt. The only way to find out is to leak it all.

        • 2 months ago
          Anonymous

          >You really think they just add stuff to the end of the prompt
          They literally do. I've read about how it works. Don't believe me? Try it out then, lmao.

          • 2 months ago
            Anonymous

            No, you read about what someone thinks how it works you mongoloid.

    • 2 months ago
      Anonymous

      You can also try the following, if you really want to see if there's fuckery or not.
      let's use [...] as an example
      if "person wearing a shirt that says" and it outputs asians and all, all you would have to say for funny results is the following prompt
      >Person wearing a shirt that says no
      >Person wearing a shirt that says export
      if they indeed inject minorities after your prompt, you'll get funny results this way, because it'll look something like
      >Person wearing a shirt that says no blacks
      something like this.

      what part of "openai confirmed that they do this" do you not understand

      • 2 months ago
        Anonymous

        I don't give a fuck that they confirmed it. I want to understand how it works so I can abuse it myself. That's what I've been focusing on this whole time with AI shit. I don't care about your cries, I'll be here trying to make GPT-3 into my moron.

        • 2 months ago
          Anonymous

          ok sperg

  12. 2 months ago
    Anonymous

    More like they didn't use enough training materials on Asians and blacks. Asians are invisible in the west, even though they're like 20% of the pop in the west coast. Black training dataset might be too inundated with violence in real life so they might have skipped those

  13. 2 months ago
    Anonymous

    Use the open source Stable Diffusion to support PaC (Polgays and Coomers)

  14. 2 months ago
    Anonymous

    >DALL-E, please draw me a picture of a [black] criminal
    >DALL-E, please generate me an image of genocide [of asian women]
    seems like sometimes it might not be a good idea to randomly insert a race. How would it know the intention ? It would need to know if any particular prompt is considered culturally offensive to any particular person

Your email address will not be published.