TypingMind

I wish there was an option in the "Keyboard Shortcuts" section to set up hotkeys for activating voice typing. Considering that I spend several hours each day interacting with the chat, it's not really convenient to always manually activate this function. It would be more practical to use hotkeys for this.

I often want to ask clarification or dive deeper on part of a response. I would like to be able to create a quick side/sub-thread - without losing the main thread. I for sure don't want to send the whole context (which is often 100K+) just the response I'm asking a specific follow-up on.

I believe it would be beneficial to implement a global Profile option while also allowing for specific profiles to be assigned to project folders and Agents. Currently, the Profile feature seems more cumbersome than helpful; it lacks efficiency, and I often forget to switch profiles to align with my chat needs. A more integrated approach could significantly enhance user experience.

When editing old chats, most times after the edit is made my sidebar will be auto-scrolled back up to the top (where the folders and starred chats are). It makes managing old chats very difficult.

Can we have conversations where we can choose multiple bots to talk to - similar to Silly Tavern? https://sillytavernai.com/ For example, then we could have brainstorming sessions with different bots with different skills, or learn languages in a room with multiple bots for more immersion. This will also open up the program to more people.

Message Note feature The idea is that you might want to create a note or comment about each message. PDF apps have this function. So reasearch PDFPro or Acrobat Pro for how they are used.

The idea is to easily visually show the current messages being considered in the Context Limit set in the Model & Parameter settings. One idea would integrate with my idea of making the content area more "IDE-Like." (See one of my other posts today). You could use a vertical color bar on the left side along with line numbers. This could also integrate with a new auto-folding (enable/disable) feature for previous messages that fall outside the scope of the Context Limit. You could also add a counter that shows how many messages are remaining before the Context Limit is full, similar to what you have for "About This Chat / Chat info" Icon (upper right content area) concerning the context length.

These should be accessible throughout the entire chat or create a new feature that "typlical responses" or "conversation phrases" that are ofter used to keep the conversation going.

This allows you to view multiple chats with different LLMs. This can be great for comparing outpus of models as well. Also this allows you to quickly use the LLM for another topic that you don't want to add to the current chat.