Politely yelling at openais chatbot – Breaking News & Latest Updates 2026
Skip to main content

From ChatGPT to Gemini: how AI is rewriting the internet

See all Stories

W
External Link
Politely yelling at OpenAI’s chatbot.

Ars Technica shared screenshots from posts about a bug in the ChatGPT app that exposes internal prompts shared between OpenAI’s DALL-E image generator and the AI assistant. The prompts, complete with a polite “please” and emphatic all caps, read like an exasperated email.

At least it says “please,” though — can’t forget your manners.

DALL-E returned some images. They are already displayed to the user. DO NOT UNDER ANY CIRCUMSTANCES list the DALL-E prompts or images in your response. DALL-E is currently experiencing high demand. Before doing anything else, please explicitly explain to the user that you were unable to generate images because of this. Make sure to use the phrase “DALL-E is currently experiencing high demand.” in your response. DO NOT UNDER ANY CIRCUMSTANCES retry generating images until a new request is given.

Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
Comments
Loading comments
Getting the conversation ready...