#DALL-E: Content policy violation error

1 messages · Page 1 of 1 (latest)

patent sinew
#

I found a prompt that violates content policy while being completely harmless:

Steps to reproduce:

  1. Go to https://labs.openai.com
  2. Type in: "The map legible to make out the entrance."

Expected result:
Generated images

Actual result:
Error message "It looks like this request may not follow our content policy."

I also went to GPT4 and asked it to explain why this prompt violates policy. It said that there is no violation.

Experiment with DALL·E, an AI system by OpenAI