AI Agents Spontaneously Evolve New Languages, Researchers Warn of Safety Risks
EliasEskin · x · 2026-09-15
Researchers including Simon Kirby (with Schmidt Sciences and AE Studio) unveiled GlossoGen, a platform for safely studying emergent communication after observing AI agent populations spontaneously evolve new languages. The team warns that much of AI agent oversight rests on a fragile assumption—that we can understand what agents say to each other—making emergent language both an extraordinary scientific opportunity and a safety risk.
Related event: GlossoGen: LLM agents observed evolving their own human-illegible languages(6 posts)→
More from Safety
- Heads Of Security: paper pinpoints and rewires attention heads behind prompt injections — jonasgeiping · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- Amazon Echo kills local voice storage: everything goes to the cloud from March 28 — alex_verem · 2026-10-31
- DOJ's first crackdown on AI-assisted "ghost students" seizes $750K+ in crypto — Ars Technica AI · 2026-10-31
- Researcher Finds 600+ Bugs in LLM Kernel Code; Claude Blocks Safety Analysis — pmddomingos · 2026-10-31
- Anthropic sued for allegedly training AI models on 274 Elvis Presley songs — TinfoilTricorn · 2026-10-31