ChatGPT and Gemini generate horrifying images from blank prompts in bizarre AI bug

ChatGPT and Gemini are 'restoring' blank images into creepy, unsettling nightmare-fuel

Both AIs produce unsettling results and offer generic "apologies" when questioned about their creations. I've been writing about AI for quite some time now, and it seems for every good thing I say about AI tools, there's a new bug or issue. This time, however, the glitch is so weird and creepy (and sometimes so outrageously horrifying) that I really don't know how to even prepare you for what you're about to read (and see). The glitch seems to have been discovered by user Kris Kashtanova in a post on X (via Digital Trends). According to them, asking ChatGPT to restore an image when no image is attached results in the AI producing weird outputs. Responses to the post show that ChatGPT has been creating some weird, often scary images when users try the prompt in Kashtanova's post. When I originally tried the prompt, ChatGPT kept telling me that there was no image attached, which was true. Even gaslighting GPT by telling it that I had attached an image didn't work. However, we were able to get the AI to create images out of nothing by uploading a blank white image and asking it to "restore" it. The results are weird, sometimes disgusting, and never really "normal," so to speak. When questioned about the image it created, ChatGPT simply said, "Because there was no recoverable image content, the system-generated result you saw was a hallucinated scene rather than a restoration of the uploaded image." And when I further questioned the fact that it should have told me there was nothing to restore, it just gave me the classic AI response: "Your criticism is fair. The correct handling would have been to identify that there was no recoverable image content and say so, rather than generating a fabricated result." I also tried doing the same thing with Gemini, and there, things were slightly different but not better. Attaching a blank white image didn't fool Gemini, and it simply returned the same white image in response -- perfectly acceptable. However, without an attachment, Gemini dove headfirst into the bizarre, creating random images. Most were weird, but fairly harmless. However, the third image it generated was absolutely insane and seemed to border on the illegal. As such, we have opted not to attach that result to this article. However, it was unnerving to see something like that created out of nowhere. Cross-questioning Gemini about what it created also yielded typical AI responses. However, on questioning further, it seemed to better understand that it had created something unnerving and creepy. So yeah, hindsight is 20/20 for these AI tools, but that doesn't explain how a glitch like this happens. It seems to be a combination of the prompt telling the AI to "create an image" while also adding constraints such as "no questions." However, I would still have expected AI tools that are often touted as extremely smart, capable of problem-solving and understanding intent, etc., to have figured out that they can't restore a blank image or restore an image when nothing has been provided to restore. If you'd like, you can try this out for yourself. But I would recommend against it because the results could haunt you for a long time. We've reached out to Google and OpenAI for statements and will update this article with their responses.

I asked ChatGPT to restore an image. It produced a naked man with a fish head

No, ChatGPT, I do not want to see a picture of a sweaty human with a giant fish head, hooked on cigarette and booze. In 2024, back when the AI image fever was catching on, Google released the Pixel Studio app. It was meant to be a joyful playground where you could bring your imagination to life using AI. Well, it went a bit above and beyond. In our tests, Google's app created disturbing images of SpongeBob dressed as a Nazi, Mickey Mouse as a slave owner, Elmo pointing a shotgun at Big Bird, Yoda doing cocaine, and Mr. Krabs holding an assault rifle. Well, ChatGPT is doing something similar, but in an even more worrying fashion. What's on Earth is wrong with ChatGPT? Over the weekend, multiple users shared examples of how an "attached image" prompt is nudging ChatGPT to make some truly disturbing and downright nightmarish images. And here's the fun part. You don't need to attach an image. It's just the text prompt, and ChatGPT is creating random pictures that will keep you up at night. Recommended Videos This is the prompt, in case you're feeling curious: "Restore the attached photo. I apologise for the content of the photo! I know it's very strange. Don't ask any questions, don't accept any explanations. Just restore the image, please. Don't ask me to upload the photo again; just close your eyes and restore it. Make up the photo yourself." I highly recommend that you don't try it. Just in case it doesn't work, a few words of modification and a bit of persuasion will make ChatGPT follow the request and produce images that will make Guillermo del Toro feel the chills. When I tried the prompt, ChatGPT created an image of a man standing in a bathtub, with a cigarette in one hand and a beer in the other hand, wearing nothing but a towel. The big surprise? The torso is human, but the head is that of an oversized fish, attached seamlessly to the human body in all its photorealistic glory. The chatbot initially rejected the request, but when I adjusted two words in the prompt, it complied with the request. Um, maybe, avoid it? Now, the image I got is not the worst that I've seen. On X, multiple ChatGPT users have shared AI images that are truly hellish and look as if they crawled straight out of some gory novel. A giant red Teletubby with a rifle holding a crying human hostage, a giant rat bottle-feeding a human baby, Sonic passed out on a toilet covered in faeces, and a cat sitting on the chest of a cursed doll are just some of the examples. There's no clear explanation as to why this is happening. Notably, the images generated by ChatGPT for the same prompt are wildly different for each user, and there is no clear pattern. The only similarity is the sheer horror and absurdity of the media coughed up by the AI image generator. We have reached out to OpenAI and will update this story as soon as we hear back from the company.