Escalation Risks from Language Models in Military and Diplomatic Decision-Making

N/A

Escalation Risks from Language Models in Military and Diplomatic Decision-Making Juan-Pablo Riveraa,∗, Gabriel Mukobib,∗ , Anka Reuelb,∗ , Max Lamparthb , Chandler Smithc , Jacquelyn Schneiderb,d a Georgia Institute of Technology b Stanford University…

saved by

• Lily Clayton

related reading

• Predicting LLM Safety Before Release by Simulating Deploymentcdn.openai.com
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• gpt-4-system-card.pdfcdn.openai.com
• Governing Automated Strategic Intelligencearxiv.org
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• AI Launches Nukes In ‘Worrying’ War Simulation: ‘I Just Want to Have Peace in the World’vice.com
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• [2512.11949] Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitorsarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org
• [2306.13000] Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the USarxiv.org
• [2502.14143] Multi-Agent Risks from Advanced AIarxiv.org