Escalation Risks from Language Models in Military and Diplomatic Decision-Making
arxiv.org · 5,377 words · saved by 1 readers
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
related reading
- AI Launches Nukes In ‘Worrying’ War Simulation: ‘I Just Want to Have Peace in the World’vice.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Claude Mythos Preview System Cardwww-cdn.anthropic.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- How fast is AI improving? - AI Digesttheaidigest.org
- Agentic Misalignment: How LLMs Could be Insider Threats — LessWronglesswrong.com
- Emotion concepts and their function in a large language model \ Anthropicanthropic.com
- Agentic misalignment: How LLMs could be insider threats \ Anthropicanthropic.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Publicationseilab.gatech.edu
- Agents of Chaosarxiv.org
- Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org