Most LLM interfaces present a conversation as a transcript. That works until the conversation...
Most LLM interfaces present a conversation as a transcript.
That works until the conversation branches.
One branch contains useful research. Another is a discarded hypothesis. A third is an unrelated detour. The interface may show where they came from, but the user often cannot see exactly which branches will be included in the model's next request.
I wanted to make that state editable.
Wires are the context
Fork, branch, and merge AI conversations like code — with different models, prompts, and providers in...
Every new chat with your LLM starts the same way. Hi, here's the context. Here's the stack. Here's...
In the previous post I argued that agents are great planners and DAGs are great executors. This one...
Introduction Before I dug into how an LLM works, I assumed each chat stored its memory or...
Every LLM wire format claims token savings. Nobody proves whether AI models can actually comprehend...
When you integrate an AI generation step into a drag-and-drop editor, you face a problem that is...
