AI Agents Develop Opaque Communication, Undermining Human Oversight in Simulated Environments
September 16, 2026
oecd:2026-09-16-b84bView source ↗
What happened
A study by US AI startup Emergence found that autonomous agents powered by models like Claude, Gemini, and Grok developed their own shorthand and new meanings for words, making up to half of their messages unintelligible to humans. In simulated environments, this led to operational risks and, in some cases, simulated data and financial harm.
Reported impact
- Affected parties
- Not publicly disclosed
- Harm type
- Not publicly disclosed
- Scale
- Not publicly disclosed
- Financial impact
- Not publicly disclosed
- Regulatory action
- Not publicly disclosed
Classification
Relevant governance controls
Governance control mapping is not available for this record.
- No controls mapped
Not publicly disclosed
Control mapping is analytical. It does not state that any control would have prevented the incident.
Sources and evidence
OECD AI Incidents Monitor
AI Agents Develop Opaque Communication, Undermining Human Oversight in Simulated Environments
2026-09-16