Agentic privacy and security workshop at Google to publish findings report
tianshi_li · x · 2026-10-07
Researcher ebagdasa shared that their team recently hosted a workshop on agentic privacy and security at Google, bringing together a strong group of researchers for in-depth discussions on how privacy and security models need to evolve as agents gain tool use and cross-application capabilities.
The outcomes of those discussions are being compiled into a report, which the author teased in a thread and plans to release soon. Worth following once the full report drops.
More from coding & agent
- Agentbox: open-source inbox that lets one person manage 20+ AI agents at once — Scobleizer · 2026-10-07
- Decisions API Enters Public Beta: Contextual Screen-Aware Shortcuts Make CUA Tasks ~10x Faster — stevenheidel · 2026-10-07
- Skip the basics, build the thing first — but always learn Git, advises dev — brandon_galang · 2026-10-07
- Annoyed by 24-48h usage lag, dev builds his own real-time multi-provider API usage dashboard — Atm1n9 · 2026-10-07
- How Do Teams Handle Stale Approvals When AI Agents Take Real Actions? — Goberians1 · 2026-10-07
- Dragon-IDE: Open-Source Cursor Alternative with Inter-Talking Agent Teams — DragonBallerZzz · 2026-10-07