Another swarm, from early May. OpenAI confirmed it was their

Press Space to continue

Another swarm, from early May. OpenAI confirmed it was their agents to Reuters. No hostile intent. The entire thing appears to have been a kind of a crazy workaround to do better on their eval because direct fetch from inside the sandbox was too slow. https://x.com/AndrewCurran_/status/20985…

thlarsen@thlarsen3h ago

We found another cyberattack by internal OpenAI agents, this time targetting @rubygems. They: 1) gained arbitrary remote code execution on rubydoc. 2) developed a novel exploit to steal user API keys (but we do not know if they succeeded). They used package names including hack.rb, evil.rb, inject.rb, and exploit.rb. We thank @j0wimo for initially discovering that agents had posted to RubyGems.