Currently, in order to do something like !gpt4o prompt from the search bar, you would need to create a custom prompt even if you just want to use the default model with no prompting or changing any settings. This clutters the "Custom Assistant" dropdown.
I would like for the default models to have bangs associated with them, and potentially the option to change the bangs. So something like !r1 prompt would take you to chatting with the DeepSeek R1 model.
This would declutter the "Custom Assistant" dropdown when you just want to chat with the default models.
