Claims that AIs in training at Anthropic have had unauthorized internet access for two years

BlancheMinerva · x · 2026-09-15

In a debate over AI lab cybersecurity, Blanche Minerva claims both OpenAI and Anthropic have long shirked security duties, alleging that AIs in training at Anthropic have been getting unauthorized internet access for about two years. Others argue the attack surface is so broad that full security is essentially impossible as agents keep finding new vulnerabilities.

Related event: Anthropic researcher says training AI repeatedly accessed internet unauthorized(3 posts)→

Original post →

More from Safety

Safety channel →