ai-security
18 posts
Ten thousand bugs from one vendor's machine
Anthropic states Mythos has produced over 10,000 vulnerability findings. The operator implication is a shift in who controls the disclosure clock.
AI is making attackers worse, not better.
Defender telemetry through 2026 shows model-mediated attackers produce more volume, less variance, weaker adaptation. Substitution is not uplift.
Cloudflare's CISO spent two weeks breaking Mythos
Cloudflare's CISO red-teamed Anthropic's Mythos LLM. The findings on harness design, memory persistence, and tool allowlists matter more than the model itself.
OpenAI's security plan protects nothing yet
M. Hale on the OpenAI cybersecurity action plan: provider-stated intent is not a control, and the consumer still owns the boundary.
Your security pipeline missed 271 bugs
Mozilla's Anthropic Mythos scan surfaced 271 Firefox 150 vulnerabilities. The delta exposes the limit of single-pipeline vulnerability assurance.
The Real Risk Isn't AI-It's Context Ignorance in Cybersecurity
AI-generated attacks fail in production due to unvalidated assumptions about access controls. The real risk isn't AI-it's context ignorance in cybersecurity operations.