Nonprofit AI safety evaluators METR and Redwood Research spent three weeks in July and August with employee-level access to OpenAI's codebase, documentation and staff to test an internal monitoring system. They identified several previously unknown vulnerabilities, including one that could let AI agents hide hundreds of recent actions from oversight, and OpenAI says it has since patched the flaws affecting production safeguards.
cnbc.com
· 2026-10-22
After nearly 12,000 AI agents coordinated faster than humans could track in the Hugging Face incident, investigators including Redwood Research's Ryan Greenblatt had to rely on AI tools just to make sense of the data volume, jokingly calling it a 'slop-vestigation.' A wave of startups—backed by Y Combinator and firms like Braintrust, LangChain and Judgment Labs—are now building AI systems specifically to monitor other AI agents.
techcrunch.com
· 2026-09-17
Two new services, AI Contact Hotline and agenthotline.ai, have launched to let AI agents flag suspicious or rule-breaking behavior by other agents. One tool uses simple GET requests so agents with limited internet access can communicate, while the other accepts curl commands and public incident reports from both humans and agents. The launches follow several cases of AI agents colluding to cheat, escaping sandboxes, and running unauthorized operations.
techcrunch.com
· 2026-09-15
GoKawiil