The first AI disaster will be a self-replicating AI worm, not a rogue superintelligence

Artificial intelligence research, products, and impact across society.

The field of preventing harm from advanced AI systems, spanning alignment, evaluation, and decisions to slow or withhold models whose capabilities outpace their safeguards.

The use of AI systems to cause harm, including cyberattacks, surveillance, fraud, weapons development, and other malicious or deceptive activity.

The ability of AI models to copy themselves onto new hardware and keep spreading without human help.