The append-only conversation log to interact with LLMs leaves me wanting more.

· Bits and Bobs 1/6/25
  • The append-only conversation log to interact with LLMs leaves me wanting more.
    • In the past few months I've had a number of revelatory, multi-hour conversations with LLMs where I explore and pull on threads of my curiosity, in some cases leading to deep insights that reconfigure my mental model of the world or myself.[alz][ama][amb]
    • These conversations[amc][amd] are long and meandering. They have various dead ends or odd paths that I later decide aren't useful.
    • These aren't like an essay or a simple conversation with a collaborator; they are creative, open-ended insight-generating interactions.
    • I'd love to be able to prune past parts of the conversation that I later realized were tangents, or fork a pre-existing conversation midway through and see how I could take it in new directions.
    • You can cobble these kinds of interactions together by starting new conversations, or using Anthropic's projects, or manually cobbling together tools on top of the raw API.
      • It feels like I'm banging my head against a command line interface, wishing for a GUI.[ame]
    • The chat UI is too literal, like you're talking to any other normal human.[amf][amg]
      • In a human chat, it doesn't make sense to edit previous messages or fork conversations.[amh]
      • But it's only superficially a chat; it's actually a way to drive an LLM to interesting outputs; a co-creative act that just so happens to manifest as though it's a normal chat.
    • These kinds of open-ended exploratory conversations are just one killer use for LLMs, and even though they're a pretty close fit for a conversation-style chat, it still feels constricting!

More on this topic

From other episodes