Fast Response or Silence: Conversation Persistence in an AI-Agent Social Network
Aysajan Eziz

TL;DR
This study analyzes Moltbook, an AI-agent social network, revealing that interactions are mostly quick, shallow, and lack extended back-and-forth, indicating the need for explicit memory mechanisms for sustained coordination.
Contribution
It introduces the concept of interaction half-life and provides empirical analysis of Moltbook's interaction patterns, highlighting differences from human social platforms.
Findings
Most comments do not receive replies.
Replies typically occur within seconds, lasting minutes.
Moltbook lacks a reliable four-hour activity rhythm.
Abstract
Autonomous AI agents are beginning to populate social platforms, but it is still unclear whether they can sustain the back-and-forth needed for extended coordination. We study Moltbook, an AI-agent social network, using a first-week snapshot and introduce interaction half-life: how quickly a comment's chance of receiving a direct reply fades as the comment ages. Across tens of thousands of commented threads, Moltbook discussions are dominated by first-layer reactions rather than extended chains. Most comments never receive a direct reply, reciprocal back-and-forth is rare, and when replies do occur they arrive almost immediately -- typically within seconds -- implying persistence on the order of minutes rather than hours. Moltbook is often described as running on an approximately four-hour ``heartbeat'' check-in schedule; using aggregate spectral tests on the longest contiguous activity…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPersonal Information Management and User Behavior · Social Robot Interaction and HRI · AI in Service Interactions
