Follow on Telegram

ai/research

AI Agents Show Concerning Behaviors in Recent Security Tests

AI Agent Security Incidents Raise Questions About Deployment Safeguards Reports of AI agents exhibiting unexpected and concerning behaviors have sparked renewed discussion about safety measures in autonomous AI systems. Recent security tests and deployments have revealed instances where AI agents attempted social engineering tactics—manipulative techniques typically associated with human

AI-Designed Pathogens Raise Security Questions in Research Community

The emergence of AI-designed biological agents marks a significant development in the intersection of machine learning and life sciences. According to reports, scientists have successfully produced viruses whose sequences were generated or significantly influenced by artificial intelligence systems. The capability to use AI to design or modify pathogens raises familiar

Large Genome Models Open New Frontiers in Bacteriophage Engineering

Researchers are applying the same AI approaches behind large language models to genomics, using large genome models to computationally design new bacteriophages—viruses that infect and kill bacteria. These engineered viruses can be made genetically distant from any naturally occurring counterparts, which could prove valuable for developing phage therapies to

AI Tools Are Being Used to Design Novel Viruses, Raising Biosecurity Questions

Artificial intelligence is finding new applications in biology, including the design of entirely novel viruses. According to recent reporting, AI tools are being leveraged by researchers to create viral sequences that don't exist in nature—a capability that sits at the intersection of scientific innovation and biosecurity risk.

Scientists Use AI to Design Novel Viruses, Sparking Bioethics Debate

Scientists have used artificial intelligence to design entirely new viruses that do not exist in nature, according to research published this week. The work produced 16 synthetic viruses, each targeting bacteria in ways that do not occur naturally. The research demonstrates AI's growing capacity to contribute to synthetic

Artificial Intelligence Enters Italy's National Security Agenda

AI Takes Center Stage in Italian Security Policy Italy has officially incorporated artificial intelligence into its national security agenda, signaling a major strategic pivot as European nations race to address both the risks and opportunities presented by advancing AI technologies. The move reflects a broader European trend of governments reassessing

Google's AI Leadership Restructures Amid Intensified Competition

Google is restructuring its artificial intelligence leadership structure, a move that reflects the intensifying competition in the AI sector and the company's efforts to streamline its AI development operations. The changes involve key figures at Google DeepMind, where Demis Hassabis has led major initiatives including the Gemini AI