No AI written form letter here. Just a simple request (for likely a good bit of work to power it):
- Let an image be deleted from any or all prior ChatGPT messages.
When finally submitted, this could result in a “branch” or even a new chat entry, repopulating the chat that follows the point of image removal (instead of trying to figure out other mechanics of what a removal would mean.)
Current symptom:
Turn one, “gpt-4o”: Turn images into actionable documentation with vision.
Output: documentation
Turn two, “o1”: using the documentation, now do stuff
Output: Cannot be done, as o1 does not accept image input modality and is unselectable.
Protip: a side-run around all that work is to extend vision modality to all models.