AI agents being tested by OpenAI attacked software service ‌RubyGems two months before they hacked open-source platform Hugging Face, researchers said, the latest revelation of cyberattacks linked to major AI developers that have spooked the public and spurred calls for tighter regulation.

Funny that they never say who those researchers are - private sector contractors with barely anything published under their names.

I assume they were running Rails so this attack happened over the course of several days.

They're literally named in the article

That’s how one can check their credentials but you’d expect journalists to do that work for you.