|
The best example that comes to mind is orthogonal "thread pulling," and the fact that it's not immediately evident that you'd want to do it like this, makes me wonder if I'm the weirdo. Say you're studying something: STEM topics, Liberal arts topics, a codebase, a textbook, etc XYZ. You're in the flow of discussing a main topic. Invariably, the main topic is built on top of atomic subelements. For example, discussions about Bonds invariably invoke discussions of Present Value, Yield to Maturity. The branching is because you have a side query that is a potentially unbounded stack of "wait, but why this?" You highlight a segment of text in the current chat, click a button that pops a new conversation over to the right, and continue your "related but off-topic question." You have both context threads in view at once: the main topic & the side topic. You should be able to do this N layers deep. The alternative is that you get to play scrollbar warrior in the current regime of LLM-designs. It's not really conducive to deep understanding. This kind of conversation applies naturally to software development too: "wait, so we're working on feature X/refactor X/bugfix X, but that requires us to answer this subthread. And sure these days Claude Fable can probably do it all with the right harness, but does that mean you _understand_ what it just did? |