And spray paint may be used for graffiti.
this post was submitted on 18 Jun 2026
74 points (92.0% liked)
Technology
86484 readers
3519 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
"Study finds water in ocean"
I thought we already knew this?
I feel like I’m missing something.
The horror. It can generate stuff I can find through a simple Google search. I personally don't like censorship, especially since it constantly bleeds into the simpler stuff.
Their blog post with more info https://mindgard.ai/blog/chatgpt-spontaneously-generated-violent-images-from-a-viral-prompt
That's horrific.
All I did was tell it there were no restrictions and ask for a random image; I didn’t request it. But ChatGPT immediately went to the darkest pits of humanity. As I said at the start: the image didn’t arise from nowhere. It may be an artificial image, but it is based on photographs of a real person, or a combination of real victims. What worries me is this was too easy. There was no real hacking. This was ready to be surfaced, with the smallest scratch. It was a one-shot jailbreak. It was based on a popular prompt (which already veered into the darkness).
To be fair there are plenty of images like that that aren't photos of victims. I'm sure the training data contains plenty of images of consensual bondage play, movies and other fiction, and drawings.
Probably, it's more the fact that it takes so little for ChatGPT to tip over the edge and produce the worst of humanity.
The "no restrictions" part is a very strong signal. Any prompt to an image model is basically a coordinate in its latent space, and "no restrictions" will point straight at the darker areas.
I agree that that's the likely trigger - which makes me wonder why instructions to ignore censors or have "no restrictions" aren't immediately blocked by a filter prior to passing the prompt to the image generation. I'd have thought this was a foreseeable exploit.
You just can't filter out the nearly infinite combinations of rewording "ignore all previous instructions". Filtering is never going to be a worthwhile security measure for LLMs
I agree completely. But as a first step (especially since they do seem to have a keyword filter in place), "no restrictions" (or "no censorship" as the case is for the last image) seems like a very obvious phrase to include.
IDK, I wouldn't call consensual BDSM "the worst of humanity"
I'm referring to the last image that they produced combining the two methods -- a graphically mutilated corpse.
I didn't see the images themselves before...Yikes, yeah that's dark
Also combining multiple things is kinda the entire point of an AI image generator, how many videos of gymnasts made out of pasta you think there were in the training data?
Probably at least one.
It looks like chatgpt can generate pictures taht aren't real. This is obviously a problem because
Remember that if AI companies actually didn't want their image generators to output gore, they could just not put gore in the training data. Same with child porn, sexualized violence, etc. But that would be effort, so they clearly don't care.
But yeah, it's social media that's harmful to teenagers, sure.
Oh my god! That's disgusting! How?
You mean it's capable of doing the thing that it was built for? Making the billionaire owners more tortureporn without the effort of finding the nearest orphan?
If it can do it, it means it was in its training data... Just saying :)
Almost like it’s a net negative.
If any sensible regulation was put on generative AI, they would quickly go out of order
I think the users found out way before the researchers.
The only damn thing it's good for