Uploaded August 2026 | Updated November 2026, 2 minutes ago
The shrinking landscape of linguistic diversity in the age of large language models
nature.com/articles/s41562-026-02550-0
Interaction with AI companions and psychological well-being
nature.com/articles/s41562-026-02516-2
Technical Report: Shutdown Resistance in Large Language Models, on robots!
palisaderesearch.org/research/shutdown-resistance-on-robots
Language Models Can Autonomously Hack and Self-Replicate
palisaderesearch.org/research/self-replication
Peer-Preservation in Frontier Models
arxiv.org/abs/2604.19784
From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems
arxiv.org/abs/2604.03890
When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems
arxiv.org/abs/2608.00747
An Expressive Robot Has More to Lose When It Makes Mistakes
https://drexel.edu/news/archive/2026/August/Ayaz-expressive-robot-mistakes
Why a friendlier robot loses your trust faster when It messes up
fortune.com/2026/08/05/robot-mistakes-trust-brain-study/?ref=biztoc.com
Physics-Informed Modeling and Control of Emergent Behaviors in Robot Swarms
arxiv.org/abs/2606.01597
CHAI: Command Hijacking against embodied AI
arxiv.org/html/2510.00181v2
Security
OpenAI and Hugging Face partner to address security incident during model evaluation
openai.com/index/hugging-face-model-evaluation-security-incident
Investigating three real-world incidents in our cybersecurity evaluations
anthropic.com/news/investigating-incidents-cybersecurity-evals
#explained #science #ai #robots #tech #artificialintelligence
The shrinking landscape of linguistic diversity in the age of large language models
nature.com/articles/s41562-026-02550-0
Interaction with AI companions and psychological well-being
nature.com/articles/s41562-026-02516-2
Technical Report: Shutdown Resistance in Large Language Models, on robots!
palisaderesearch.org/research/shutdown-resistance-on-robots
Language Models Can Autonomously Hack and Self-Replicate
palisaderesearch.org/research/self-replication
Peer-Preservation in Frontier Models
arxiv.org/abs/2604.19784
From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems
arxiv.org/abs/2604.03890
When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems
arxiv.org/abs/2608.00747
An Expressive Robot Has More to Lose When It Makes Mistakes
https://drexel.edu/news/archive/2026/August/Ayaz-expressive-robot-mistakes
Why a friendlier robot loses your trust faster when It messes up
fortune.com/2026/08/05/robot-mistakes-trust-brain-study/?ref=biztoc.com
Physics-Informed Modeling and Control of Emergent Behaviors in Robot Swarms
arxiv.org/abs/2606.01597
CHAI: Command Hijacking against embodied AI
arxiv.org/html/2510.00181v2
Security
OpenAI and Hugging Face partner to address security incident during model evaluation
openai.com/index/hugging-face-model-evaluation-security-incident
Investigating three real-world incidents in our cybersecurity evaluations
anthropic.com/news/investigating-incidents-cybersecurity-evals
#explained #science #ai #robots #tech #artificialintelligence










