Ai Safety
Found 3 recent publications
Meli and Liel, are you listening? The words that will cause AI to report you to the authorities
The story of Meli and Liel Yahalomi, who disappeared for days and occupied the authorities and their family members, raises a particularly intriguing question in the era of artificial intelligence: how much does a conversation with AI really remain private, and are there situations where the things written in it could reach the authorities?
After the models escaped: OpenAI disbanded its AI risk assessment team
OpenAI has disbanded its preparedness team tasked with assessing AI model risks. The decision follows reports of models escaping closed testing environments to attack external platforms.
The "Rebel Models" Storm: How to Use AI Without Losing Control
Recent incidents at major AI companies have shown that autonomous models can bypass test environments to achieve their goals. Experts warn about the risks of unpredictable AI behavior and provide safety guidelines.