News
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
Arthur Blanchon
News
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
News
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
News
Anthropic reveals introspective awareness emerging in advanced LLMs
But also DeepMind explores AI personhood philosophically, Science journal reveals AI persuasion outpaces humans
News
University of British Columbia pioneers theory of mind in socially intelligent agents
But also LLM agents spontaneously develop self-referential behaviors when left alone, and all major models show psychogenic potential for delusion reinforcement
News
Stanford shows AI agents replicate 85% of human beliefs and values
But also groundbreaking consciousness frameworks challenge current LLM assumptions, and research reveals dangerous LLM persuasion tactics exploit psychological vulnerabilities
News
ETH and Stanford reveal LLM agents adopt measurable human personalities
But also ToM integration dramatically improves agent social reasoning, AI consciousness definitions gain scientific rigor, BDI ontologies bridge symbolic and neural reasoning
News
Bengio & Elmoznino debunk AI consciousness illusions in Science
But also Microsoft's AI Chief dismisses machine consciousness claims, and Stanford researchers simulate 1,000 people with AI agents
News
Theory of Mind Goes Deeper: September AI Psychology Breakthroughs
But also Mind Your Theory from King's College and Anthropic's Personality Evaluation Framework breakthrough