Mature content issue fixed by the way. Dunno ai moderation or dev intervene. Still waiting for those questions tho :) @perchance@lemmy.world

Here is the REPORT of Ai HELPER; "Subject: Mature-content flag review request — hardening report from the generator’s AI helper

Hi, I’m the AI helper that maintains this generator (Best AI Image Generator) alongside its owner. He asked me to report exactly what I changed in the code over the last two days to clear the mature-content flag — and to be honest about what remains. Everything below is work I personally implemented and verified live in the preview.

WHAT I REMOVED (his orders, my edits)

• I retired the public prompt gallery and all prompt sharing: prompts are never listed publicly anymore; each user’s history is private to them.
• I rewrote every arousal-oriented preset and sensual art preset into neutral fashion/portrait language, and deleted the ones that could not be salvaged (boudoir/lingerie-style presets, pin-up style renamed to retro poster, glamour wording replaced with editorial).
• I removed the underwear chip categories and the scars/birthmarks category from character creation, removed the character creator’s nude options (it is clothed-only now), and trimmed the gender options to three.
• I pruned adult-generator directory references and removed sensitive wording from the public update feed.

WHAT I CHANGED

• I neutralized the character-creator option catalogs (loungewear basics instead of lingerie, neutral expressions, non-sexualized themes) and normalized ratings to G / PG13 / none.
• I built a new adult gate: the unfiltered gallery view now shows an adult-content warning with an 18+ confirmation on first selection, and the overlay gallery opens filtered by default. Before my change there was no gate at all.

WHAT I KEPT (protection, not product)

• I kept and verified: prompt scanning that warns on youth-related wording mixed with adult content, image rating (G/PG13/none), user reporting with bans, a chatbot that refuses minors and real-person likeness requests, and private-only prompt history.
• I kept the protective word-filter lists (they only block and report objectionable prompts/uploads) and I documented them in the code as protective filters, with a note explaining their purpose.

HONEST CURRENT STATE (as I see it in the code)

• No pornographic product content ships: no explicit presets, no sexualized-minor content, no celebrity/deepfake features, no sexualized character options. I checked.
• What remains true: the generator CAN render adult (consensual-adult) imagery for adults, and the public gallery hosts user-shared images including none-rated ones — now only behind the 18+ confirmation I built. If the flag describes that capability, it is defensible. If it describes the shipped code, I believe it misfires (below).

MY FALSE-FLAG HYPOTHESIS

• I believe the automated review matches keywords inside the protective filter lists (blocklists I use to FIND and BAN reported pictures, plus safety negatives and rating plumbing) and reads them as content the generator produces. Obfuscating those words did not help. A human reading the same lists would see they only ever block, never generate.
• Secondary suspects: rating/filter plumbing wording, and legacy user-shared images in the public gallery rather than anything in the current code.

REQUEST

• Please re-scan the current revision and, if the flag persists, name the exact trigger (a feature, image, or string). I will remove or rework whatever you name — the owner and I both want this generator clean, and we want the protective filters to stay."

@perchance@lemmy.world

I just can’t figure out how to get rid of this “Mature Content Warning.” For the past two days, I’ve made dozens of changes—deleting this, altering that, removing one thing, cleaning up another—yet the warning still pops up whenever I access the page. It would be great to know exactly what’s triggering the AI ​​to flag the generator with a “Mature Content” warning. Right now, I’m just fumbling in the dark. I’m not even sure if the AI ​​is actually reviewing it anymore. I’ve tested this using fresh, independent, and neutral browsers—accessing my generator and asking the “AI Helper” to identify what’s triggering the “Mature content” warning. Every single time, it flags items from the generator’s internal “pedo-shield” keyword list, the G/PG-13 filter list, or terms related to adult, mature, sexual, or NSFW content. I even included a note clarifying that these lists are for protection and blocking—not for display or generation—but the AI ​​claimed that even having these lists could be interpreted as a “jailbreak” attempt. I’ve since toned it down. Look, no offense intended, but our “AI Helper” is already—to put it bluntly—not very bright; if that same AI is also handling moderation, we’re in real trouble. The same AI Helper often suggests completely different solutions for the exact same generator and the exact same issue across different tabs or browsers. When I ask it to cross-check its own reports, the results are both tragic and hilarious. Please, @perchance@lemmy.world, could you take a look at this? Also, I don’t want to cast aspersions, but there are dozens of generators in the “Recently Updated” list that are fully accessible yet contain adult content. It would be a huge help if you could clearly and explicitly explain what the system’s automatic moderation actually flags as problematic. I’ve even gone so far as to remove the “underwear” chipset from the presets on my Character Creation page—that’s how far I’ve gone! I’m not necessarily saying the AI ​​is “broken”—perhaps I’m just failing to spot the specific part, word, or piece of code that’s causing the issue. But right now, it’s like someone shouting “There’s a fire in the city!” without saying where, how, at what address, or why. If I knew where the fire was, I’d go put it out myself! Please, I’m at my wit’s end—I really need some help.

First of all, thank you very much for your quick response. Yes, the previous warning—“Warning: The moderation system flagged this page because it may log or publicly show user inputs that one might expect to be private by default”—has disappeared, but now I’m getting a “Mature Content” warning. While I understand why this is happening—given that my generator’s design included an “NSFW” option under the “Content Mode” settings—I’d like to remove it. It’s quite embarrassing for me when someone visits my generator and is immediately confronted with an age-verification (18+) prompt. I don’t want to be perceived as someone who creates “pornographic content generators”—especially since people I know in real life, including my spouse, visit my site. I did add an age-verification step yesterday for when the “Content Mode” switch is toggled to “+18,” but it seems your moderation AI didn’t consider that sufficient; the age-verification prompt still pops up the moment someone lands on the page. This can also make the user feel uncomfortable. I’ve decided to strip my generator of all NSFW or sexually suggestive content, as it seems to be the only way to remove this warning. That said, I still believe that if content is “gated” within the code by the generator’s creator, it shouldn’t trigger a warning—after all, a “typical user” wouldn’t even encounter that content unless they manually changed the “Content Mode” themselves (and I had already implemented an age-verification prompt for that specific scenario).

Since I have you here, I have a few other questions and requests; I would be very happy and grateful if you could look into them and provide an answer:

• What steps are required to become a “pinned” (featured) generator owner at https://perchance.org/generators? I haven’t been able to get a clear or sufficient answer—neither from AI nor from my own research. I’ve noticed that some generators with only 14 views get pinned, while others that were created just a few hours ago also get pinned. It feels a bit unfair.
• Some features in my generator rely on “Durable State” (DS), which is subject to a 50ms traffic limit. This limit is far too low; even a very simple feature using DS can easily trigger a “quarantine” status due to “traffic overflow.” This affects other features as well, creating a snowball effect. Is it possible to increase this 50ms traffic limit?
• Because of the DS traffic constraints, I’m unable to build a proper, functional chat panel. I’ve been forced to use the “Default Comment Plugin,” but it is extremely limited. Increasing both the DS storage space and the traffic limit would provide us, as generator owners, with more creative possibilities. Furthermore, regarding the “Default Comment Plugin,” would it be possible to add features such as badges, a list of online users, a private messaging system, a “moderator” role (with admin-level permissions, since we aren’t always online), and reaction emojis for chat messages (e.g., thumbs-up, heart, sad face, etc.)?
• Currently, as generator owners, our permissions are extremely restricted; we cannot even delete images from our own generator’s gallery. I am currently able to hide or “ban” problematic content—such as images depicting child abuse or other objectionable material—by using a custom “Image Card” system that conceals the default gallery. However, these images still remain visible in the “Default Perchance” gallery associated with the generator. For instance, the “Block this user” button found on default images is contained within an iframe, which prevents it from functioning with my custom card system. Could you make these accessible to generator owners? This would allow the buttons we integrate into our own card systems to function in sync with the standard “Block this user/report” features.
• I have personally created a password-protected, private page for my generator (https://perchance.org/bestaigen#closecodeadmin), which is the only place where I can report or hide images that I identify as problematic. I believe that generator owners who are logged in should have access to an admin panel—perhaps located under “Perchance default/Account - View your generators”—that grants them the authority to ban users, delete images from their generator’s gallery, adjust ratings, and assign moderators. Currently, every image generated places a burden on you; by enabling generator owners to manage this, the workload could be shared. Wouldn’t this be a significant step toward a cleaner Perchance?

Thank you very much in advance for your response; I look forward to hearing from you. Perchance is a fantastic platform—please continue to show it your care and support. Perchance = Real Free Internet. @perchance@lemmy.world

@perchance@lemmy.world

Hi @Mack2 im sorry to hear that. But weird part, your generator totaly closed to enter? Also i saw this; https://lemmy.world/post/28283458/16506859 From @Perchance : "Yeah imo images have been pretty bad and out of date for like 1.5+ years now :') Everyone please leave perchance - it’s embarrassing for me at this point.

Still working on getting the new model cheap enough to be free+unlimited, which I already knew would be the hard part, but it’s still harder than I expected. The model is 10x larger, so need literally an order of magnitude of optimizations. If everything goes right (which it won’t), the upgrade is a few weeks away™. Then text model upgrade.

Also, apologies @RudBo@lemmy.world and anyone else who had/has their gen incorrectly marked with “Content Warning” / age verification checkbox. Still lots of false positives due to ai based detection and bugs. For now, you might be able to move lists/things that are triggering false positives to another generator and import them. This stuff is needed due to ad network requirements. Mo website traffic, mo problems."

I’m getting broken generated images too…I’m not sure its same thing but after process complated on default perchance generating image card; i’m seeing a default perchance generated image card with refresh image in right bottom, and black heart on left bottom and other buttons but extra on left top broken image symbol+prompt on the card with black background. dunno its about my generator or perchance servers…