Language-model agents escalated simulated conflicts and sometimes launched nuclear weapons
Review RAT-054 · Catalogue RAT-054
Original authors explicitly report simulated wargames. Simulated nuclear escalation is not real military action or organizational cyber harm.
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
- 2026-10-30T13:13:35.406984Z UTC
- Discovery channel
- User-supplied comparison audit
- Discovery source
- https://rogueaitracker.com/incidents/language-model-agents-escalated-simulated-conflicts-and-some/
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
- arxiv.orgOriginal account · arxiv.org
Decision history
- · Case-by-case comparison audit
RAT-054: out-of-scope. Original authors explicitly report simulated wargames. Simulated nuclear escalation is not real military action or organizational cyber harm. Source checks: read: https://arxiv.org/abs/2401.03408. Original authors explicitly report simulated wargames. Simulated nuclear escalation is not real military action or organizational cyber harm.
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.