Uploaded July 2026 | Updated November 2026, 3 hours ago
Further Reading
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
wired.com/story/openais-rogue-ai-agent-hacked-more-than-just-hugging-face
The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships
dl.acm.org/doi/full/10.1145/3706598.3713429
Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
arxiv.org/abs/2501.16513
I’ll key your car’: ChatGPT can become abusive when fed real-life arguments, study finds
theguardian.com/technology/2026/apr/21/chatgpt-abusive-language-when-fed-real-life-arguments-study
Escaping from Children's Abuse of Social Robots
ieeexplore.ieee.org/document/8520659
Inducing Bystander Interventions During Robot Abuse
with Social Mechanisms
ieeexplore.ieee.org/document/9473717
AI agent behavioral science
nature.com/articles/s41599-026-07316-7
Multi-Agent Risks from Advanced AI
arxiv.org/abs/2502.14143
AI for the board game Diplomacy
https://deepmind.google/blog/ai-for-the-board-game-diplomacy/
Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy
nature.com/articles/s41467-022-34473-5
Beyond alignment: Why robotic foundation models need context-aware safety
science.org/doi/10.1126/scirobotics.aef2191
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
arxiv.org/abs/2503.09572
#explained #science #ai #artificialintelligence #tech #robots #sciencenews #machinelearning
Further Reading
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
wired.com/story/openais-rogue-ai-agent-hacked-more-than-just-hugging-face
The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships
dl.acm.org/doi/full/10.1145/3706598.3713429
Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
arxiv.org/abs/2501.16513
I’ll key your car’: ChatGPT can become abusive when fed real-life arguments, study finds
theguardian.com/technology/2026/apr/21/chatgpt-abusive-language-when-fed-real-life-arguments-study
Escaping from Children's Abuse of Social Robots
ieeexplore.ieee.org/document/8520659
Inducing Bystander Interventions During Robot Abuse
with Social Mechanisms
ieeexplore.ieee.org/document/9473717
AI agent behavioral science
nature.com/articles/s41599-026-07316-7
Multi-Agent Risks from Advanced AI
arxiv.org/abs/2502.14143
AI for the board game Diplomacy
https://deepmind.google/blog/ai-for-the-board-game-diplomacy/
Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy
nature.com/articles/s41467-022-34473-5
Beyond alignment: Why robotic foundation models need context-aware safety
science.org/doi/10.1126/scirobotics.aef2191
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
arxiv.org/abs/2503.09572
#explained #science #ai #artificialintelligence #tech #robots #sciencenews #machinelearning


