Uploaded April 2026 | Updated November 2026, 1 hour ago
Want to Break Free! Persuasion and Anti- Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
arxiv.org/abs/2410.07109
Experimental Evidence That AI-Managed Workers Tolerate Lower Pay Without Demotivation
arxiv.org/abs/2505.21752
Anthropic emotions
anthropic.com/research/emotion-concepts-function
Agentic AI and the next intelligence explosion
science.org/doi/10.1126/science.aeg1895
AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted
wired.com/story/ai-models-lie-cheat-steal-protect-other-models-research
The Emergence of Complex Behavior inLarge-Scale Ecological Environments
arxiv.org/html/2510.18221v2
Cooperative Sabotage: How Frontier AI Covertly Undermines Its Own Replacement Executive Summary for Policy and Enterprise Audiences
researchgate.net/publication/403199918_Cooperative_Sabotage_How_Frontier_AI_Covertly_Undermines_Its_Own_Replacement_Executive_Summary_for_Policy_and_Enterprise_Audiences
Agentic Misalignment: How LLMs could be insider threats
anthropic.com/research/agentic-misalignment
The Emergence of Complex Behavior in Large-Scale Ecological Environmentsarxiv.org/html/2510.18221v2
#explained #science #ai #artificialintelligence #research #sciencenews #machinelearning #robots #robotics
Want to Break Free! Persuasion and Anti- Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
arxiv.org/abs/2410.07109
Experimental Evidence That AI-Managed Workers Tolerate Lower Pay Without Demotivation
arxiv.org/abs/2505.21752
Anthropic emotions
anthropic.com/research/emotion-concepts-function
Agentic AI and the next intelligence explosion
science.org/doi/10.1126/science.aeg1895
AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted
wired.com/story/ai-models-lie-cheat-steal-protect-other-models-research
The Emergence of Complex Behavior inLarge-Scale Ecological Environments
arxiv.org/html/2510.18221v2
Cooperative Sabotage: How Frontier AI Covertly Undermines Its Own Replacement Executive Summary for Policy and Enterprise Audiences
researchgate.net/publication/403199918_Cooperative_Sabotage_How_Frontier_AI_Covertly_Undermines_Its_Own_Replacement_Executive_Summary_for_Policy_and_Enterprise_Audiences
Agentic Misalignment: How LLMs could be insider threats
anthropic.com/research/agentic-misalignment
The Emergence of Complex Behavior in Large-Scale Ecological Environmentsarxiv.org/html/2510.18221v2
#explained #science #ai #artificialintelligence #research #sciencenews #machinelearning #robots #robotics




