GlossoGen: new framework studies when LLM agents develop languages humans can't understand

lucy3_li · x · 2026-09-15

Researchers at Schmidt Sciences released a blog post introducing GlossoGen, a framework for studying the conditions under which LLM agents develop their own languages that humans cannot understand. The work highlights a fragile assumption underlying AI agent oversight: that we can understand what agents say to each other. The framework and accompanying paper offer a systematic way to probe emergent inter-agent communication and its safety implications.

Related event: GlossoGen: LLM agents evolve languages humans can't understand(4 posts)→

Original post →

More from Safety

Safety channel →