I'm still shocked that there isn't basic functionality in chatgpt that allows you to fork conversations to have subtopical conversational threads off of a main one.
For example, I'm asking deep philosophical questions, or maybe reaching for a STEM concept slightly beyond my understanding, and that inevitably requires me to ask subquestions (eg "okay wait, what are Conformal Fields?"). Doing so still forces me to do a linear conversational format, and it just isn't functional.
Blows my mind that with all the great big AI minds at OpenAI they still can't do basic functionality.
-- edit --
Like seriously, for some of us old heads, imagine having this in undergrad: a professor in your pocket that can handle your arbitrarily stupid recitation questions, one on one, with infinite patience. I think I could have aced electrodynamics and Calc III instead of just pulling Bs.
Unfortunately, it looks to only support single subthreads. But my questions have questions sometimes. I want to subthread conversations to arbitrary depth. If they can subconvo once, they can do it arbitrarily.
Oof. I won't be using this. The implementation is terrible: just forks a new tab in my browser (at least on Firefox). I want a horizontally scrolling view, clickable highlights that specify my subconversational contextual focus.
I think I have always been able to have branching conversations via editing a comment.
The interface remembers both the old and new conversation thread and you can switch between them.
It seems like the new "Branch in new chat" feature mostly creates a new chat at the top level rather then the existing functionality of editing a comment and branching in the same chat.
Thanks for sharing. I unzipped the .xpi file and threw it through a couple of static malware analyzers. Not seeing anything. Doesn't mean it's safe, but means I might be dumb enough to try it. Looks pretty cool.
For example, I'm asking deep philosophical questions, or maybe reaching for a STEM concept slightly beyond my understanding, and that inevitably requires me to ask subquestions (eg "okay wait, what are Conformal Fields?"). Doing so still forces me to do a linear conversational format, and it just isn't functional.
Blows my mind that with all the great big AI minds at OpenAI they still can't do basic functionality.
-- edit --
Like seriously, for some of us old heads, imagine having this in undergrad: a professor in your pocket that can handle your arbitrarily stupid recitation questions, one on one, with infinite patience. I think I could have aced electrodynamics and Calc III instead of just pulling Bs.