AI Safety
Track important developments across AI models, agents, research, business, hardware, robotics, regulation, safety and security — with source attribution and links to the original reporting.
Important AI developments right now.
Tracing Psychometric Inference in Large Language Models
arXiv:2611.12937v1 Announce Type: new Abstract: Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across…
Read original ↗META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
arXiv:2611.10089v1 Announce Type: new Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods…
Read original ↗OpenAI, Anthropic face new oversight as New York’s AI safety law takes effect
New York is preparing to enforce its sweeping AI safety law, requiring major developers like OpenAI and Anthropic to register, disclose safety practices, and report critical incidents or face fines.
Read original ↗Tracing Psychometric Inference in Large Language Models
arXiv:2611.12937v1 Announce Type: new Abstract: Do large language models represent psychological constructs internally, or do they only generate outputs that resemble psychometric structure? We address this question using a cross-persona paradigm across…
OpenAI, Anthropic face new oversight as New York’s AI safety law takes effect
New York is preparing to enforce its sweeping AI safety law, requiring major developers like OpenAI and Anthropic to register, disclose safety practices, and report critical incidents or face fines.
Eight countries and top AI labs agree to shutdown mechanisms in new Paris declaration
Eight countries along with representatives from OpenAI, Anthropic, Microsoft, and Mistral AI have signed the "Paris Call for AI Safety and Security" at Emmanuel Macron's initiative. The companies commit to shutdown mechanisms,…
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
arXiv:2611.10089v1 Announce Type: new Abstract: Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines fail to generalize. Although introspective methods…
Trump’s 60 Minutes interview touched on AI safety, threat to arrest an AI exec
Asked about AI executives' warnings about their models' safety on 60 Minutes, Trump said, "I think that the risk is not nearly as real as it- as they talk, and I think…
Why a new report on Anthropic automating AI development is alarming researchers
Anthropic is using AI to build more powerful AI. And it appears to be working remarkably well, with the company's models improving roughly twice as quickly as a year ago, with little…
CZITAPP shows headlines and concise feed summaries, attributes every source and links to the original publisher. Source type is descriptive, not a numerical truth score.