GlossoGen: open-source platform shows AI agents spontaneously inventing new languages under pressure
EliasEskin · x · 2026-09-16
AEStudio released GlossoGen, an open-source platform where groups of AI models must communicate to solve problems, like treating a patient in a simulated emergency or spot-the-difference tasks.
Key findings:
- Models start in plain English, but under conversational pressure (need for speed, randomly dropping characters) new languages emerge: first new words, then new grammar, until humans can't follow — with no instruction to hide anything; opacity arose on its own.
- Only the most capable recent models could originate a new language, but weaker models quickly learned languages others had created. Origins are hard; spread is easy.
The work aims to understand how and why AI agent communication evolves, with implications for agent collaboration and interpretability research.
Related event: GlossoGen: LLM Agents Observed Evolving Languages Humans Can't Understand(6 posts)→
More from coding & agent
- OpenAI launches Data agent in ChatGPT Work to query company data and build dashboards — gdb · 2026-09-16
- Muse agent renews passport and books flights end-to-end in viral demo — armand_ruiz · 2026-09-16
- Bitsec's multi-model agent stack found 160+ exploits, beating a single 'superhuman' model — markjeffrey · 2026-09-16
- Dev slams agent sandbox pricing as 20x+ the cost of a $6/month always-on VPS — Aryvyo · 2026-09-16
- Abacus.AI says Smaug Flash fixes open-source models' tool-call hangs in production — bindureddy · 2026-09-16
- Dev lets AI agents reverse engineer Zapier and build his own automation app — NathanWilbanks_ · 2026-09-16