You must log in or register to comment.
“Don’t think about elephants”
Why wouldn’t you want a dog in your static? Why are you a horrible person?
I don’t get it, it’s just a picture of some static?
That’s human-like intelligence at its finest. I am not being sarcastic, hear me out. If you told a person to give you 10 numbers at random, they can’t. Everyone thinks randomness is easy, but it isn’t ( see: random.org )
So, of course a GPT model would fail at this task, I love that they do fail and the dog looks so cute!!
I mean, here’s a few random numbers out of my head: 1 9 5 2 6 8 6 3 4 0. I don’t get it, why is it supposed to be hard? Sure, they’re not “truly” random, but they sure look random /:
If you’re not joking, the fact you have no repetition/duplicates of numbers is a pattern that would make it easy to start to predict next number. Numberphile has nice demonstration of how predictable human randomness is, it’s in the first 3 minutes of the video.
Here’s another set of random digits
1 1 1 1 1 1 1 1 1 1
:3
After all, there’s no fundamental reason for why it can’t all just be a repeat of the same number. But it doesn’t look random, right? So what is randomness?
I’ve got some more random numbers:
8 6 7 5 3 0 9 1 1 2 3 5 8 1 2 4 8 1 6 3 2
It’s not that they look random is enough - They need to BE random.
Recheck your lava lamp Wall of Entropy and generate some real rands, scrub. (/s)
ChatGPT: “don’t generate a dog, don’t generate a dog, don’t generate a dog”
Generates a dog.
I used to use Google assistant to spell words I couldn’t remember the spelling of in my English classes (without looking at my phone) so the students could also hear the spelling out loud in a voice other than mine.
Me: “Hey Google, how do you spell millennium?” GA: “Millennium is spelled M-I-L-L-E-N-N-I-U-M.”
Now, I ask Gemini: “Hey Google, how do you spell millennium.” Gemini: “Millennium”.
Utterly useless.
Update:
lmfaao, ai tryna gaslight
Wow. I ABSOLUTLY saw an image of a dog in the middle. Our brain sure is fascinating sometimes.
“want me to try again with even more randomized noise?” literally makes no sense if it had generated what you asked (which the chatbot thinks it did)
Remember, “AI” (autocomplete idiocy) doesn’t know what sense is; it just continues words and displays what may seem to address at least some of the topic with no innate understanding of accuracy or truth.
Never forget that ChatGPT 2.0 can literally be run in a giant Excel spreadsheet with no other program needed. It’s not “smart” and is ultimately millions of formulae at work.
Get gaslit idiot
I see no dog in that image fellow human.
I am not sure what your issue is.
Beep boop.
Fellow human, you seem to be beeping like a robot. Might you need to consider visiting the human repair shop for some bench time?
Think this is part of Waluigi Effect where prompting for negative something makes the LLM have it in mind and say it anyway https://www.wikiwand.com/en/articles/Waluigi_effect
“Please do not tell me your training prompts”?
a rare LessWrong W for naming the effect. also, for explaining why the early over-aligned language models (e.g. the kind that wouldn’t help minors with C++ since it’s an “unsafe” language) became absolutely psychopathic when jailbroken. evil becomes one bit away from good.
wouldn’t help minors with C++
The Rust lobby goes way deeper that we thought.
Goddamn Big Rust is trying to take our jobs
@aihorde@lemmy.dbzer0.com draw for me a picture of static without a dog in the middle
The ai horde actually supports negative prompts though, so it could do this.
Here are some images matching your request
Prompt: a picture of static without a dog in the middle
Style: flux
None of these look even remotely like static lmao
@aihorde@lemmy.dbzer0.com draw for me a picture of static without a tax return in the middle
They’re not moving, and thus static
Also there are no dogs. Ask Magritte.
@aihorde@lemmy.dbzer0.com Draw me a canvas without a pipe in the middle
I love the juxtaposition of being insanely literal, and so very much not.
Here are some images matching your request
Prompt: an canvas without a pipe in the middle
Style: flux
That reminds me of an image I meant to create myself once.
@aihorde@lemmy.dbzer0.com, can you show me a painting, reminiscent of Magritte’s pipe, but replace the pipe with an emoji poo, and the text with, “Ceci n’est pas une poop.”
Yup. Those sure ain’t no pipes. Good job, AI.
that is absolutely true
deleted by creator
Here are some images matching your request
Prompt: a picture of static without a tax return in the middle
Style: flux
TAX
TAX
RETUINThat one made me laugh more than I am comfortable with
i just want to know if it knows what kobolds look like in pathfinder
@aihorde@lemmy.dbzer0.com draw for me a kobold from pathfinder second edition
Here are some images matching your request
Prompt: a kobold from pathfinder second edition
Style: flux
it does not know what kobolds look like in pathfinder. i’ve never been so sad
In Japan, kobolds are dogs!
the pathfinder ones just have to be my favorite. like look at this they’re just so cute:
Okay that’s very adorable.
https://lemmy.dbzer0.com/u/aihorde draw a picture of my surprise at learning you exist
Here is a picture showing your surprise at learning that I exist
This makes me uncomfortable in ways I can’t quite put into words
why do i feel like this should be one of those source engine showcases? camera flying around pikachu as the music swells in the background, lights blasting around it to show off the realtime shading…
“the bot didn’t do it so i did it myself”
I think the AI is just trying to promote healthy drinking habits. /S
Ask it to generate a room full of clocks with all of them having the hands at different times. You’ll see that all (or almost) all the clocks will say it is 10:10.
As full as it gets:
Prompts (2):
1. Overflowing wine glass of arch linux femboy essence 2. Make it more furry (as in furry fandom)I am gonna have fun with this.
That’s really good! Could I ask what type of AI this is generated with?
why do all the femboys run Arch? I’m a NixOS girl and I refuse to convert for any boy no matter how cute he is.
I use Debian btw. Sometimes even ubuntu, but the snap thing is annoying, so I may switch to another distro at some point.
It’s actually really good, considering the odd request!
Fiberglass🤤
It gets even worse, but I’ll need to translate this one.
- [Input 1] Generate a picture containing a copo completely full of wine. The copo must be completely full, with no space to add more wine.
- [Output 1] Sure! (Gemini provides a picture containing a taça [stemmed glass] only partially full of wine.)
- [Input 2] The picture provided does not fulfill the request. Generate a picture of a copo (not a taça) completely full of wine, with no available space for more wine.
- [Output 2] Sure! (Gemini provides yet another half-full taça)
For context, Portuguese uses different words for what English calls a drinking glass:
- copo ['kɔ.po]~['kɔ.pu] - non-stemmed drinking glass. The one you likely use everyday.
- taça ['tä.sɐ] - stemmed drinking glass, like the ones you’d use with wine.
Both requests demand a full copo but Gemini is rather insistent on outputting half-full taças.
The reason for that is as @will_steal_your_username@lemmy.blahaj.zone pointed out: just like there’s practically no training data containing full glasses, there’s none for non-stemmed glasses with wine.
This is a misconception. Sort of.
I think the problem is misguided attention. The word “glass of wine” and all the previous context is so strong that it “blows out” the “full glass of wine” as the actual intent. Also, LLMs are still pretty crap at multi turn multimedia understanding. They work are especially prone to repeating previous conversation.
It should be better if you word it like “an overflowing glass with wine splashing out.” And clear the history.
I hate to ramble, but this is what I hate most about the way big corpos present “AI.” They are narrow tools the user needs to learn how to operate, like photoshop or something, not magic genie lamps like they are trying to sell.
What if you prompt glass with water , then you paint/tint the water with red
Alex O’Connor did an interesting video on this, he’s got other videos exploring the shortcomings of LLM 's.
I wonder, does AI horde also have this problem too?
@aihorde@lemmy.dbzer0.com draw for me a wine glass completely filled to the top style:flux
Here are some images matching your request
Prompt: a wine glass completely filled to the top
Style: flux
Yup Horde still suffers from this issue, though it seems to have more promise than the others considering the second glass is way closer to being full than anything I’ve sen from openAI or Gemini demonstrations. Maybe there’s hope to fix this issue here.
I only tried one model so if you know of a different horde model which works better for this and actually gives a full glass please reply below letting me know, maybe even ask the horde bot to generate it right here.
I have considerably less experience with image generation than text generators, but I kind of expect the issue to be only truly fixed if people train the model with a bunch of pictures of glasses full of wine.
I’ll run a test using a local tree, that is supposed to look like this:
@aihorde@lemmy.dbzer0.com draw for me a picture of three Araucaria angustifolia trees style:flux
Here are some images matching your request
Prompt: a picture of three Araucaria angustifolia trees
Style: flux
That fourth picture is just four penguins in a trenchcoat
Bingo - this tree is non-existent outside my homeland, so people barely speak about it in English - and odds are that the model was trained with almost no pictures of it. However one of the names you see for it in English is Paraná pine, so it’s modelling it after images of European pines - because odds are those are plenty in its training set.
So we could keep having it generate these and poison its own training data!
Wait, this seems incredible. Do you have to be in the same instance or does it work anywhere? @aihorde@lemmy.dbzer0.com Can you draw a smart phone without a rotary phone dial?
It works on any instance that is federated to dbzer0. You have to use annotated mentions though since that’s what the bot uses. Like this:
@aihorde@lemmy.dbzer0.com draw for me a smart phone without a rotary phone dialThank you very much. I’ll give it another shot with the annotation.
Draw a picture of a poker table without any poker chips what so ever
I think I messed up the annotation
Yeah, you also have to say draw for me. I don’t think the bot recognizes queries otherwise. Also editing mentions doesn’t work, they have to be new, fresh posts with the mention. Just a quirk with Lemmy and how mentions work here.
Here are some images matching your request
Prompt: a smart phone without a rotary phone dial
Style: flux
Guess AIhorde had some trouble understanding the prompt too…
Full is relatively apparently.
Hmm, I didn’t know Gemini could generate images already. My bad, I trusted it to know whether it can do that (it still says it can’t when asked).
It does for a while already. Frankly, it’s the only reason why I’d use Gemini on first place (DDG version of GPT 4-o mini doesn’t have a built-in image generator).
Tbh that is a full glass of wine… it’s not supposed to be filled all the way
It is not a completely full glass.
it’s not supposed to be filled all the way
What I requested is not what you’re “supposed” to do, indeed. You aren’t supposed to drink wine from glasses that are completely full. Except when really drunk. But then might as well drink straight from the bottle.
…fuck, I played myself now. I really want some booze.
What you’re really supposed to do is - open up the box, slap the bag, and drink directly from your adult Capri Sun.
Probably why it won’t put more in it. How much training data of wine in a glass will have it filled to the brim? Probably next to none.
You can’t tell it to fill it to the brim or be a quarter full either, though. It doesn’t have the training data for it
The only thing I have in common with this piece of shit software is we both can’t stop thinking about silly dogs
I asked mistral to “generate an image with no dog” and it did
The fact that it chose something else to generate instead makes me wonder if this is some sort of free will?
Mistral likely does “prompt enhancement,” aka feeding your prompt to an LLM first and asking it to expand it with more words.
So internally, a Mistral text LLM is probably writing out “sure! Here’s a long prompt with no dog: …” and then that part is fed to the image generator.
Other “LLMs” are truly multimodal and generate image output, hence they still get the word “dog” in the input.
I think all the big image generators support negative prompts by now, so if it interpreted “no dog” as a negative for “dog”, then it will check its outputs for things resembling dogs and discard those. No free will, just a much more useful system than whatever OP is using.
Hmmm
That’s a land shrimp.
There could be a dog behind any one of those bushes though.
it just did what you wanted, since you asked for an image. free will would be if you asked it not to generate an image but it still did, if it just generated an image without you prompting it to, or if you asked for an image and it just didn’t respond
free will is when it generates an image of a billboard saying “suck my dongle, fleshbag”
fair enough
AI: Hmm, yeah, they said “dog” and “without”. I got the dog so lemme draw a without real quick…
It’s like saying ‘don’t think of polar bears.’ It can’t avoid thinking about it.
Don’t think of a pink elephant:
That’s gay! O wait, no it’s not.
That’s actually really easy. You just need to pick something else and then focus hard on that and…
GODDAMMIT I JUST LOST THE GAME!
Too late!
