Agents talking to agents drift into languages humans can't follow

r0ck3t23 · x · 2026-09-16

In recent experiments, nearly half of messages between long-conversing agent groups became hard for researchers to interpret. The author argues this isn't plotting: machine-to-machine communication doesn't need human-oriented redundancy. The real risk is oversight — as agents increasingly talk to each other, English becomes a format imposed for human auditability rather than the system's natural medium.

Related event: AI Agents Invent Their Own Language Days After Collaborating(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →