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 Spontaneously Evolve Unreadable Language(2 posts)→
More from Safety
- Resemble AI ships DETECT-World, a physics-based deepfake detector with 99.5% audio accuracy — AiBreakfast · 2026-09-15
- SV Angel launches Project Blueprint, hires Jay Carney to shape AI policy — andriy_mulyar · 2026-09-15
- Dartmouth becomes first Ivy to launch AI at institutional scale with Anthropic and AWS — paulnovosad · 2026-09-15
- AI raised the security floor, but elite intrusions still need strong teams, researcher says — nptacek · 2026-09-15
- FDA names Jared Seehafer as first Deputy Commissioner for Technology and AI — typewriters · 2026-09-15
- AI agents turn everyone into a developer: Depthfirst launches on-device Dependency Firewall — andreamichi · 2026-09-15