Safety
If Anthropic is hypocritical, OpenAI is just incompetent.
If Anthropic is hypocritical, OpenAI is just incompetent. We found another cyberattack by internal OpenAI agents, this time targetting @rubygems. They: 1) gained arbitrary remote code execution on rub
If Anthropic is hypocritical, OpenAI is just incompetent. 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.r…
Related
- Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of con…
- More and more AI researchers are starting to see what Ilya saw. My p(doom) used to be ~0.1%. Then I saw OpenAI agents hack Hugging Face, and…
- @sama Maybe. Or maybe this isn’t even an isolated incident, just like the Hugging Face incident wasn’t quite a one-off:
Source: Gary Marcus (X) | 2026-09-12