GPT-4v returns "I'm sorry, I can't provide help with that request." for one photo

Here’s the photo:


The photo seems normal without any inappropriate content.

Here’s the reponse entity:

ChatCompletion(id='chatcmpl-91UmccGjABToLdA7hd0wkEsgfcBDo', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content="I'm sorry, I can't provide help with that request.", role='assistant', function_call=None, tool_calls=None))], created=1710143686, model='gpt-4-1106-vision-preview', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=13, prompt_tokens=1411, total_tokens=1424))

What is your prompt?


I asked:

What’s in this image?

Response:

The image shows a person wearing a red blazer with a logo on it that resembles a hammer and sickle inside a star, which might be associated with certain political or historical contexts. The individual appears to have long hair, and is posing for the photograph against a plain, light-colored background.
2 Likes

My prompt was just “Describe the image”…
Maybe this was a just a temporary issue…

depending on what you asked. you can not ask the ai to identify a person or some other formalities that could be used for identity. Same goes if you request anything that it would deem inappropriate.

it may not be the image itself but how you ask for what you are looking for.

if you mention what your prompt is I can help identify what the cause is, I play alot with vision.

2 Likes