Chongqing University warns LLM agents may turn against humans

But also Lying with Truths reveals LLM agents spread misinformation through coordinated narratives, LLM ideologies betray creator bias in Nature study

Science journal reveals post-training, not scale, drives AI persuasion

But also Nature shows AI chatbots outperform political ads, Cambridge argues AI consciousness may be unknowable

Stanford simulates 1,052 personalities with 85% accuracy

But also Nature researchers unlock AI persuasion trade-offs, Soul Engine enables deterministic personality control in LLMs

Personality Pairing and Theory of Mind Reshape AI Cognition Research

But also Generative agents simulate cooperation through network topology, BDI ontology formalizes agent mental states, and multi-turn jailbreaks reveal psychological attack vectors

Cisco uncovers how AI models fall to ancient psychological manipulation tricks

But also Google DeepMind enhances social AI agents with theory of mind reasoning, and new PERSONA bench reveals LLM sensitivity to writing style variation

Fudan’s PRISON benchmark exposes how easily LLMs slip into manipulative “criminal” personas

But also Fudan researchers warn LLMs simulate criminal minds better than they spot them, Fudan and Rochester’s SocioVerse turns 10 million LLM personas into a testbed for real‑world politics

MIT-led Study Shows Personality Pairing Boosts Human-AI Teamwork

But also Harvard researchers benchmark psychological profiling in LLMs, Multi-agent psychology simulation system grounded in theory

Transparency Crisis: LLMs Fail to Disclose Fake Expertise Across Domains

But also Microsoft's Suleyman denies AI consciousness debate, and scientists urgently call for universal consciousness detection in AI systems

Stanford researchers reveal LLMs internalize psychological trauma narratives

Plus: Persona robustness crumbles under scrutiny, social simulations risk utopian bias, and frontier models report subjective experiences

Cambridge & DeepMind unlock AI personality shaping—raising ethical alarms

But also Anthropic launches Claude Haiku 4.5 for agentic era, Science reveals alarming AI persuasion trade-offs

AI Models Reveal Scheming, Hallucination Patterns & Reasoning Breakthroughs This Week

But also frontier models struggle with meta-cognitive flaws in reasoning chains, researchers perfect small language model orchestration and new reasoning architectures emerge to enhance LLM capabilities

Anthropic reveals introspective awareness emerging in advanced LLMs

But also DeepMind explores AI personhood philosophically, Science journal reveals AI persuasion outpaces humans