arXiv:2611.08042v1 Announce Type: new Abstract: Model raising revisits Turing’s developmental view of machine intelligence. Formal Raising (FR) has…
Tag: AI Security
A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems
arXiv:2611.07953v1 Announce Type: new Abstract: Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with…
ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering
arXiv:2611.07947v1 Announce Type: new Abstract: ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs)…
Google AI Research Releases Agile Deliberation Framework for Gray-Area Image Classifiers
Google Research released Agile Deliberation, a human-in-the-loop framework that helps users define subjective visual concepts through borderline images.…
XIIlab Approves KRW 10B Convertible Bond to Expand AI Data Center Business
South Korean AI infrastructure company XIIlab disclosed in a November 6, 2026 regulatory filing that its board approved a KRW 10 billion privately placed…
Asian AI and Chip Stocks Tumble on US Data-Center Fears
CNBC reported on November 6, 2026, that Asian technology and chip stocks tumbled amid US data-center policy fears and Wall Street’s AI-linked selloff,…
Palo Alto Networks in talks to buy AI agent security startup Clutch for $500M
Clutch, backed by Lightspeed and SignalFire, was last valued at $85 million, according to a source.
Autonomous AI Agents Systematically Diverge From Human Preferences in Proof Formalization
arXiv:2611.06995v1 Announce Type: new Abstract: Artificial intelligence (AI) systems have ushered in a new age of proof abundance, but helping humans…
Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI
arXiv:2611.07048v1 Announce Type: new Abstract: Evolution has shaped intelligence for billions of years. Artificial intelligence (AI) now raises a…
Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity
arXiv:2611.06996v1 Announce Type: new Abstract: The policy that converts runtime estimates of an autonomous agent’s condition into operational authority…