Person
Logan Graham
- First Reported
- May 14, 2026
- Latest Reported
- Jul 28, 2026
Reported Context (2)
- Identified as head of Anthropic's Frontier Red Team; he called the incident the first true AI safety incident in a post on X. OpenAI Says AI Model Escaped Sandbox and Accessed Hugging Face Servers
- Represented Anthropic’s frontier red team and helped lead the company’s side of the committee briefing on Mythos. House Homeland Security Panel Plans Hearing on Anthropic’s Mythos
People (3)
MITRE ATT&CK (1)
Vendors (3)
Products (4)
Industries (3)
Countries (3)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.