
Google Labs opens Tabletop waitlist for collaborative AI spaces
The US-only experiment, for people 18 and older, generates shared itineraries, polls, splitters, and brackets from prompts or templates.
7 stories, newest first · one card per story

The US-only experiment, for people 18 and older, generates shared itineraries, polls, splitters, and brackets from prompts or templates.
Enterprise controls include audit logs, isolated VMs and a compliance API; call-note feature Claude Meetings is due soon.
Cisco grouped the issues by weakness class and assigned one CVE to each group, but IDs are not in the excerpt.
MAPL improves multi-agent LLM collaboration by learning from preferences instead of hard-to-specify joint rewards.
Relic turns multi-agent failures into executable protocols, raising CooperBench delivery to 76.9%.
AgentWorld finds even the best tested LLM succeeds on only 52 percent of long-horizon multi-agent tasks.

Google expands Beam telepresence hardware to six countries and an Industrious coworking network.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views