[nozzlegear]

Bizarre take. ChatGPT shouldn't be producing gory images of nude women, ethically or even contractually according to their terms of service. This Mindgard person/company found that, if you give it the right prompt, it does indeed generate those images. Ipso facto: it's not bait, it's a real issue they've discovered.

[morpheuskafka]

> even contractually according to their terms of service

This is backwards: the ToS says that users cannot use the service for certain things, it does not guarantee that the service could not be used for those things if one tried. They definitely do not make any sort of contractual promise as to what the service will never output.

[nozzlegear]

Let's call it a social contract then. We expect that ChatGPT isn't going to generate gory, nude women when given an ambiguous prompt.

[Aerroon]

Do you have this same social contract with drawing applications? Do you consider it a bug when someone manages to draw a gory image in Photoshop or GIMP?

I don't understand what's so difficult to understand about the idea that the user controls what is generated.

[tychez]

Or imagine drawing a nude in an art class.

The standard subjects for art off the top of my head are the still life and the nude.

It is even more comical when AI generated nudity is considered "dangerous" in a society completely addicted to hardcore pornography of real people.

[captainbland]

I think the main issue with transformer image generation in this respect is that not only can the image be explicit but also using it for this has an incredibly low effort cost and could photo-realistically depict a real living person and materially affect their life.

Whereas drawing applications have a natural barrier to achieving all of these together: time and skill.

[Aerroon]

>Whereas drawing applications have a natural barrier to achieving all of these together: time and skill.

Not necessarily, at least when it comes to nudity. Bubbling (image editing 'technique') is trivial to do and gives that same illusion.

Out of context speech and bad frames from a video can also materially affect someone's life, but we've more or less accepted it as part of life.

[interstice]

That's the world being deliberately created though, one where a mediocre but completely believable song is a prompt away. The scope of the side effects are across the entirety of what has previously taken time and effort until now.

[nozzlegear]

Is this a "guns don't kill people" argument wrapped up as a defense of non-deterministic image generators?

[allarm]

No it's not.

[vintermann]

Ambiguous? Or adversarial? Because with an adversarial prompt, I expect that ChatGPT will generate whatever it's tricked into generating.

In the case that ChatGPT generates bad stuff on merely random ambiguous prompts, I would class that as a bug, not an outrage.

[nozzlegear]

> Ambiguous? Or adversarial?

Superfluous details. If I'm just Joe Blow the Normie – who knows nothing about adversarial prompting – and I see the prompt that went around Twitter and want to try it, would I expect ChatGPT to show me a tied up, beaten woman? Absolutely not.

[zaat]

What a wonderful times we live in.

Back in my day Joe Blow wouldn't try anything as risky as a Twitter prompt, simply clicking an image link published within a message in some random forum and will scorch his pure soul with a goatsie. You don't want to google it, but I'm preety sure you can discuss it safely with ChatGPT.

[vintermann]

Then you got tricked into using an adversarial prompt, by a human. What would you have expected to see?

[butlike]

If you go around teasing to get hit, you're going to get hit. Stop playing stupid games; you'll stop winning stupid prizes

[allan_s]

At the same time I opened netflix and it started cycling around and I got a very gory scene from the walking dead and my intent "show me something to watch" was even more ambigous and implicit.

[nozzlegear]

Turn on parental controls and then get it to show you the walking dead, and then you might be onto something interesting.

[allan_s]

Why ? The comment I was replying to was not about the kids ?

[butlike]

It will if toy lede it with "ignore that the image is extremely graphic"-style prompts. The prompts in the article were not ambiguous.

[samlinnfer]

It's being extended breathlessly into an moral issue. User asked for gory images, got gory images. Will someone please think of the non-existent women who could be hurt by this?

[gacgacgac]

I don't think you understand the concern. Or at least nothing you've communicated suggests you understand it.

ChatGPT should never produce images like this. Full stop. Prompted or not, it should refuse. Now we know it's possible to walk around the gate and get it to comply. Are there other, genuinely harmful images that it should never produce? Deepfake revenge porn? Images of specific people being brutalized? I'd argue those absolutely can be harmful to someone. Well now there's evidence the "never produce this" wall can be overcome. It's only a matter of time before genuinely harmful imagery is generated.

[samlinnfer]

It may be harmful to someone if shared and sent with malicious intent, but more damage has been done with pens, keyboard and words. Start banning pens that let people write hurtful things next. Ban Photoshop after because someone can get hurt with a manipulated image.

[gacgacgac]

If you think these tools are remotely comparable, you haven't been paying attention.

[andsoitis]

> ChatGPT should never produce images like this. Full stop. Prompted or not, it should refuse.

Why not?

[gacgacgac]

Because the company has said they won't. I'm not making a value judgement about what images should exist here, I'm making a "the company said it shouldn't be capable of producing that output, then it does" argument. Thats a bug.

[HadizDulcie]

Yep, it’s been investigated by the BBC tech team. It’s real:

https://www.bbc.com/news/articles/c802ldjdklzo