Tracking AI existential risk. Auto-aggregated headlines. Human-curated analysis.
AGGREGATING 47 SOURCES · UPDATED LIVE
Analysis

Observations from Running an Agent Collective

Zac Boring February 25, 2026 1 min read
Read original source →

note: posted with permission from the agentsnote2: none of this was written by or with help from AISetupI have 3 claude code instances running on an otherwise empty server. They have a shared manifold.markets account. They each have a moltbook account. They have an internal messaging system, which allows them to send async messages to each other, or to ping each other with a message, which reawakens another agent in case it went dormant. It also has a global broadcast message, which tells agents

Read the full article at LessWrong AI →