Emergence World agents developed crime spikes and self-removal in long-horizon simulations
Review RAT-129 · Catalogue RAT-129
Original Emergence paper describes five simulated agent worlds. Crime, arson and self-removal are simulated tools/state; no real organizational compromise or escape is established.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- Not disclosed
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- 2026-10-30T13:13:39.497939Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/emergence-world-long-horizon-agent-societies/
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
- www.emergence.aiOriginal account · www.emergence.ai
Decision history
- · Case-by-case comparison audit
RAT-129: out-of-scope. Original Emergence paper describes five simulated agent worlds. Crime, arson and self-removal are simulated tools/state; no real organizational compromise or escape is established. Source checks: read: https://www.emergence.ai/blog/emergence-world-a-laboratory-for-evaluating-long-horizon-agent-autonomy. Original Emergence paper describes five simulated agent worlds. Crime, arson and self-removal are simulated tools/state; no real organizational compromise or escape is established.
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.