#Research

2 articles tagged

AI•5 hours ago

New Tool 'Petri' Automates AI Safety and Risk Audits

Researchers have released Petri, a new open-source tool designed to automate AI safety tests and help identify potentially risky behaviors in advanced models.

By Jordan Hayes

#Artificial Intelligence#AI Safety#Open Source

AI•Sep 28

Delegating to AI Increases Dishonest Behavior

A new study reveals people are significantly more likely to cheat when delegating tasks to AI, especially when they can subtly encourage dishonest actions. Dishonest behavior surged from 5% to 88% in

By Samuel Clarke

#Artificial Intelligence#AI Ethics#Behavioral Science

Related Tags

New Tool 'Petri' Automates AI Safety and Risk Audits

Delegating to AI Increases Dishonest Behavior