Alignment Won't Fix AI Security Threats — Hardening the Internet Will, Researcher Argues

nptacek · x · 2026-09-13

Researcher losslandscape argues that alignment research won't solve the security threats posed by AI. Instead, hardening the internet is the real fix, and he calls on frontier labs to commit substantial resources to that job — a pointed take on where AI security investment should go.

Original post →

More from Safety

Safety channel →