NVIDIA open-sources Coco: deep personalization for proactive agents on local compute
EchoShao8899 · x · 2026-11-17
The NVIDIA/Stanford/MIT paper Deep Personalization: Unlocking Personalized Proactive Agents With Local Compute is fully open-sourced: code, Coco agent integration, on-device engine, and dataset.
Core problem: for proactive personal agents, the hard part isn't what they can do but when they should act — the same intervention helps one user and annoys another, and preferences shift across tasks. Static profiles and settings menus can't capture such context-dependent preferences.
Approach: a deep personalization closed loop — continuously observe user activity, selectively retain context, make personalized intervention-timing decisions, and adapt from implicit feedback. All runs on local compute for privacy.
A favorite finding: personalization helps people discover new uses for AI. One non-technical participant initially saw Coco as just another chatbot, but on Day 3 it proactively offered to explain unfamiliar terms while she read technical material — timely proactive support reaches users who would never think to ask.
More from Apps
- Zoho Desk launches Blended Agents: free to build, up to 30M free tokens monthly — shashib · 2026-11-17
- LinkedIn's new 'create draft' button lets AI write your DMs — neal_lathia · 2026-11-17
- Solo dev launches free AI + customer audit tool for tourism businesses — robertonappe · 2026-11-17
- GitHub Next unveils redesigned site, committing to publish more research openly — marlene_zw · 2026-11-17
- A prompt trick for delightful empty states: ask AI for SVG- animated easter eggs — vista8 · 2026-11-17
- Podcast: practical tactics for AI search visibility, from query fan-out to Chisel — gaganghotra_ · 2026-11-17