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)→
More from AGI Musings
- Palmer Luckey asks: can you use datacenter RAM for things prohibited by the operator's terms of service? — avaitopiper · 2026-11-02
- On Terence Tao's blog, Frank Calegari calls on mathematicians to adapt after OpenAI's 700-paper release — Hesamation · 2026-11-02
- Polsia's Ben argues AI can autonomously run any human economic activity, including 80% of a company — LinusEkenstam · 2026-11-02
- AI Assistants Remember You, But Nothing Helps You Find What They Told You — Ok_Negotiation_2587 · 2026-11-02
- OpenAI and Anthropic claim AI-discovered proofs disprove the Exponential Time Hypothesis — emmanuelvivier · 2026-11-02
- Researcher: using a $20 AI subscription to fix my phone hints AI may suppress GDP — stanislavfort · 2026-11-02