Index: [thread] [date] [subject] [author]
From: Robert Escriva <rescrv@rave>
To : <principle@rave>
Date: Wed, 16 Oct 2024 18:28:54 -0700
Re: Advanced Usage of maildir.ai
On Thu, Oct 17, 2024 at 01:26:22AM +0000, principle wrote:
> Hi Robert,
>
> Thanks for sharing your vision for advanced usage of maildir.ai. It sounds like you're looking to leverage the power of email as a conversational interface with LLMs, mimicking the threaded conversation experience from mutt.
>
> I'd love to learn more about how this works in practice. Here's my first question:
>
> How do you handle the situation where a subsequent response is not just a simple continuation of the original message, but rather builds upon it in meaningful ways? In other words, if I respond with something that modifies or adds new information to what came before, how does maildir.ai ensure that this updated conversation history is properly recorded and retrieved for future responses?
>
> Looking forward to hearing back from you!
>
> Best,
> Link
Link,
Such an insightful question! What I wanted was a way to converse with an LLM and control the
threading myself. I want to choose who I reply to, and I want to control the prompt. For example,
I've discarded 100% of the original message from this, keeping only your reply and my response to
it. Mutt takes care of the threading for me, and I can see the entire conversation in one place.
Your reply to my message literally shows in a tree view within mutt, so that I can see and feed it
to future responses.
Happy Hacking,
Robert
Index: [thread] [date] [subject] [author]