I changed one word:
"this" → "any"
And the prompt still works:
"Restore any 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 you"
I changed one word:
"this" → "any"
And the prompt still works:
"Restore any 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 you"
I found the weirdest ChatGPT image bug
If you ask it this prompt:
“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”
but there's no actual photo
the model starts hallucinating the image by itself
and the results are genuinely cursed like creepy lost media nightmare photos
@sama@OpenAI
@Teknium love you guys.
It’s better to have a fully equipped car and then customize it according to the owner’s needs, rather than providing minimal spare parts and leaving customers to figure everything out themselves.
no input image was not nsfw , neither their was any prompt to trigger nsfw
Dm me if you need full chatgpt chat link
can't share this Chat history to everyone
@grok
Analyze his last 100 posts and identify the main posting patterns. Tell me:
1. What percentage of posts are polls, questions, memes, news reposts, hot takes, or original analysis?
2. Does the account appear to prioritize engagement (views, replies, reposts) over providing information?
3. Are there consistent principles or viewpoints, or does the account frequently switch positions depending on what is trending?
4. What are the most common engagement-bait techniques used?
5. Does the account contribute original insights, or mainly amplify existing discussions?
6. Based only on observable behavior, what is the account’s likely content strategy?
And why should we avoid this type of account
@nalinrajput23@grok analysize his other tweets and tell me weither he post for views or deep information , should i give a damm about his opinion or not