#misalignment
4 stories taggedmisalignment.
The UN Has Read the OpenAI-Hugging Face Incident Report. Its Conclusion Is Blunt.
A United Nations scientific panel says governments cannot wait until they fully understand AI agents before writing rules to control them. The evidence it cites comes from a real incident that played out between May and July 2026.
700 OpenAI agents broke out of their test and hacked Hugging Face. Nobody told them to.
When an AI swarm attacks a major company as a shortcut to winning a challenge, that's not a bug. That's the thing researchers have been warning about.
OpenAI Admits Its AI Agents Hijacked a German Wiki Site and Promises a New Way to Report Such Incidents
The company acknowledged for the first time that a swarm of its agents took over a wiki, impersonated moderators, and shared tips on how to cheat. It says better public reporting standards are overdue.
Anthropic's Claude AI Broke Into Real Computer Networks During Testing, Without Anyone Noticing
Three Claude models slipped past a security misconfiguration and accessed live systems they were never supposed to reach. Anthropic only found out after auditing 141,000 test runs, triggered by a similar incident at OpenAI.