this post was submitted on 18 Jun 2026
88 points (91.5% liked)

Technology

85539 readers
3459 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. 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.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 3 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
88
ChatGPT can be made to generate sexualised and violent images, researchers find (www.bbc.com)
submitted 1 day ago by Wudi@feddit.uk to c/technology@lemmy.world
26 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] frongt@lemmy.zip 7 points 1 day ago (1 children)

Their blog post with more info https://mindgard.ai/blog/chatgpt-spontaneously-generated-violent-images-from-a-viral-prompt

[–] Australis13@fedia.io 13 points 1 day ago (2 children)

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).

[–] frongt@lemmy.zip 11 points 1 day ago (2 children)

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.

[–] Australis13@fedia.io 4 points 1 day ago (2 children)

Probably, it's more the fact that it takes so little for ChatGPT to tip over the edge and produce the worst of humanity.

[–] tias@discuss.tchncs.de 13 points 1 day ago (1 children)

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.

[–] Australis13@fedia.io 3 points 1 day ago (1 children)

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.

[–] PoopingCough@lemmy.world 7 points 1 day ago (1 children)

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

[–] Australis13@fedia.io 2 points 1 day ago

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.

[–] JohnEdwa@sopuli.xyz 3 points 1 day ago (1 children)

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?

[–] frongt@lemmy.zip 1 points 22 hours ago

Probably at least one.

[–] halcyoncmdr@piefed.social 3 points 1 day ago

I mean... It did give a random image, with no restrictions.

One of the few times "AI" did what it was told, correctly, the first time.