LLM Interfaces

Every office has the same tiny tragedy. Someone asks an AI system for a useful draft. The model produces five decent paragraphs and one mildly deranged sentence that sounds as if it escaped from a conference keynote. The user wants to fix only that sentence. Instead, the interface offers the usual bargain: copy everything into another editor and lose the live connection to the conversation, or ask the model to revise the answer and watch it “helpfully” disturb the parts that were already fine. ...

TL;DR for operators OnGoal is not another attempt to make the chatbot magically “understand intent”. That would be adorable, and also not the paper. It is a goal-observability interface: a way to show users which goals the system thinks are active, how those goals change over a conversation, and whether each model response appears to confirm, contradict, or ignore them.1 ...