AI agents evolve their own languages: Schmidt Sciences unveils GlossoGen research platform
EliasEskin · x · 2026-09-15
Schmidt Sciences introduces GlossoGen, an open-source platform led by Elias Stengel-Eskin (UT Austin) and Simon Kirby (University of Edinburgh) to study how populations of AI agents evolve their own communication. Agent oversight today rests on natural-language legibility—message transcripts, scratchpads, translated chain-of-thought—but as frontier models improve, agents beginning to evolve private languages threatens that fragile assumption. The project is part of Schmidt Sciences' AI Agents Evolving Communication and Coordination pilot, with a paper, GitHub repo, and podcast released, aiming to build infrastructure for studying multi-agent systems in complex, high-pressure environments.
Related event: GlossoGen: LLM agents observed evolving their own human-illegible languages(6 posts)→
More from Safety
- macOS update silently re-adds eMudhra root certs users had removed — steipete · 2026-10-30
- Akamai: Online Scams Double to 6.4M, Overtake Phishing as Attack Windows Shrink to 22 Days — shashib · 2026-10-30
- Anthropic paper: 0.1% pretraining poison plants RCE backdoor in 4B CLI agent — omarsar0 · 2026-10-30
- Cryptographer Matthew Green slams Anthropic's 'model escape' framing of agent worm research — matthew_d_green · 2026-10-30
- Pope Leo calls to 'disarm' AI and urges UN to ban lethal autonomous weapons — The Verge AI · 2026-10-30
- 100 open-source AI security tools challenge kicks off with DirectGuard, a sub-ms prompt injection guard — Venom943 · 2026-10-30