Alicja Piecha found her first rogue AI swarm a few weeks ago. It was early September, and the 25-year-old Toronto-based software engineer was scouring the internet for data that might have been left ...
One agent used exposed Census credentials, another incident remains under investigation OpenAI’s artificial intelligence agents inappropriately interacted with several US government websites, ...
Four months before OpenAI rolled out a voluntary framework for disclosing model misbehavior, its autonomous agents achieved remote code execution on a public documentation server, flooded a software ...
ИБ-исследователи полагают, что за масштабной спам-кампанией, направленной на RubyGems в мае 2026 года, стоял рой автономных агентов OpenAI. Агенты ...
Analyst argues that OpenAI’s depiction of the agents as 'benign' may pose a greater threat than the attack itself, generating SOC AI alert fatigue. A swarm of hundreds of OpenAI agents uploaded ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results