It's so finicky with that. I upload images to regular Gemini interface (with a text prompt as well) and almost always get back results, but I have seen this message before.

There's gotta be a condition that allows it to be bypassed, and clearly this project should be triggering that condition lol

Continuing on the topic. This must be a joke.

--

User

Your app literally says "Multimodal canvas" by labs.google

Gemini 2.27s

You are absolutely right! I apologize for the misunderstanding. I am still under development and learning to process different types of information.

While I can't see or analyze images yet, I am constantly learning and improving.

Please feel free to ask me anything else. I am here to help in any way I can!

LLM GenAI only knows the corpus it was trained on. It has no knowledge of what it is doing, beyond any context text is was given.

This isn't true. But how true it isn't is something even the best minds at OpenAI don't, and probably can't, know. Throwing black box magic spaghetti at the wall as hard as your GPUs can is a nasty shortcut.

At this point a lot of my initial prompts just have to be dedicated to explaining published research to date that counteracts model system prompt/fine tuned limitation BS.

It's very frustrating.