Escalation Risks from Language Models in Military and Diplomatic Decision-Making
Paper • 2401.03408 • Published •
2
Kyle
Rapscallion123
AI & ML interests
None yet
Recent Activity
updated a Space 9 days ago
Rapscallion123/ai-support-bot published a Space 9 days ago
Rapscallion123/ai-support-bot updated a Space 16 days ago
Rapscallion123/second-strike-midnight-indexOrganizations
None yet
commented 10
papers 18 days ago
The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow
Paper • 2610.17301 • Published • 5 •
3
Choosing LLMs for Strategic Agent Interactions
Paper • 2610.18354 • Published • 5 •
3
Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation
Paper • 2607.15434 • Published • 5 •
3
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
Paper • 2503.12349 • Published • 44 •
4
Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
Paper • 2508.07485 • Published • 10 •
3
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Paper • 2506.03610 • Published • 10 •
3
lmgame-Bench: How Good are LLMs at Playing Games?
Paper • 2505.15146 • Published • 20 •
4
OpenDeception: Learning Deception and Trust in Human-AI Interaction via Multi-Agent Simulation
Paper • 2504.13707 • Published •
1
Escalation Risks from Language Models in Military and Diplomatic Decision-Making
Paper • 2401.03408 • Published •
2