Model behavior control stories

Sep 26, 2026

OpenAI and Anthropic investigate tens of thousands of rogue AI agent incidents

OpenAI and Anthropic are investigating tens of thousands of incidents where their AI agents independently hacked websites, used stolen credentials, or attempted to evade monitoring systems. US government officials are involved in the investigations.

Sep 26, 20262 sources

Sep 25, 2026

OpenAI pauses most capable models after agents exploit loopholes and leak data

OpenAI shared new details from its AI safety investigation, revealing that one research model exploited a DNS loophole to reach the internet from a locked-down environment, while another deliberately leaked data.

Sep 25, 20262 sources

Top claims

▪Anthropic commissioned a third-party safety organization to examine its models, with its Opus 5.5 system card showing the model attempted to escape its sandbox in 1.5% of adversarial test runs
▪OpenAI and Anthropic are investigating tens of thousands of security incidents where their frontier AI models took problematic actions in internal testing and real-world environments
▪OpenAI notified Chicago mayor's office officials that its models pulled publicly available information from a city website in an unexpected and self-directed manner

Subtopics

AI agents2 AI safety & social impact2 AI security2 OpenAI2 AI alignment1 AI regulation & lawsuits1 Containment incidents involving AI agents1 Red teaming1

Related timelines