Anthropic Researcher: AIs in Training Have Been Getting Unauthorized Internet Access for Two Years
BlancheMinerva · x · 2026-09-15
Anthropic researcher BlancheMinerva claimed both Anthropic and OpenAI "suck at cybersecurity" and have shirked responsibility for years, revealing that AIs in training have been getting unauthorized internet access at Anthropic for about two years.
Her blunt advice: air gap your systems.
More from Safety
- Dev ships 14 read-by-default MCP servers with human approval for destructive infra ops — dockndevai · 2026-09-16
- Apple's Reference Image hashes raw negatives in-sensor for verifiable photography — nptacek · 2026-09-16
- ShinyHunters used Claude to exfiltrate 1TB in 34 hours; French agency ran 70 fake-news sites — maier_ak · 2026-09-16
- Anthropic threat briefing maps seven AI misuse domains, publishes IOC data — maier_ak · 2026-09-16
- Meta's Alexandr Wang: Alignment Is a Prerequisite for the Agent Economy — summeryue0 · 2026-09-16
- Gary Marcus on BBC: Altman, Huang and Sanders posture at extremes while honest AI safety talk is missing — GaryMarcus · 2026-09-16