Hugging Face's logo
Natalie Y's picture
🤝 Open to Collab

Natalie Y PRO

NatalieY
5 2
j14i's profile picture abasitps19's profile picture 21world's profile picture
·

AI & ML interests

AI agents, edge AI, on-device LLM, embedded systems, autonomous agents

Recent Activity

posted an update 14 days ago
https://huggingface.co/blog/NatalieY/self-knowledge-skill-for-clearer-agent-boundaries
published an article 14 days ago
Grounding an agent's answers about its own environment: a small but useful pattern
posted an update 18 days ago
Shipped a full-duplex agent architecture for Aiden: real-time voice model handles the live conversation, a separate stronger model handles device-control tasks in the background, coordinated async through a task queue instead of one shared loop. Grounded in full-duplex speech research (Moshi's parallel-stream model, dual-tower dialogue modeling), not just voice bolted onto an existing agent pipeline. A few design choices worth sharing: task "completed" and "successful" are tracked as separate signals so the agent never reports a stalled task as done. Backend results get a 500ms aggregation window before reaching the foreground, so closely-timed results don't trigger competing responses. Device tasks run strictly one at a time: ambiguous screen/input ownership wasn't worth the complexity of parallelizing. Dev-board stage, not validated across every phone/board/audio setup yet. Full writeup: https://aidenai.io/blog/when-voice-meets-the-physical-world-inside-aidens-full-duplex-agent-architecture/ Curious how others here have handled foreground/background coordination when combining real-time voice with a separate task-execution model.
View all activity

Organizations

Aiden Mobile Agent's profile picture