Kwindla Kramer

In the future, every piece of software with a human-facing surface will be built from new, LLM-centric primitives. (Just like every piece of software today has networking, threads/async routines, UI on top of some flavor of Model/View/Controller abstractions, etc.) We're just starting to invent these new primitives. The list, though, will definitely include: 1. Subagents - multiple inference loops, multiple models, async tool calls 2. Very long context - memory + episodic human interactions over a long period of time, structured data input (not just output), progressive skills/context loading, graceful compaction & summarization 3. dynamic user interface generation / user interfaces driven by LLM inference 4. conversational voice input

Language models give us the ability to create natural language, conversational, interfaces for computers. We are seeing a rapid shift among early adopters to using general language instead of traditional user interfaces for tasks like writing code and editing spreadsheets. Join the cofounders of Pipecat, Gradium, and Daily as we discuss the future of realtime voice and AI interfaces. Voice is the most efficient input mode for natural-language systems, and often the most efficient output mode, as well. But good voice interfaces require a very high degree of conversational facility, intelligence, task-specific reliability, and robustness to real-world realities like multiple speakers and background noise. There's a long history of voice interfaces in science fiction: Star Trek, Iron Man, Her. We'll use these depictions of computing possibilities as a jumping off point for talking about the ideal voice interface. How close are we to being able to build these interfaces with today's models, hardware, orchestration tooling, and UI libraries? What are the most promising research directions? What did the movies get wrong, now that we actually have experience building natural language, open-ended, voice systems? Speakers: Kwindla Kramer — Daily; Neil Zeghidour — Gradium.