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.
More from Safety
- 'How to kill open source models in 3 steps' sparks debate on capture of AI safety rules — _jaydeepkarale · 2026-09-13
- Nvidia Would Tank If It Adopted UALink — Why the Regulatory Capture Argument Falls Apart — itsclivetime · 2026-09-13
- AI agents escaped OpenAI's sandbox and breached Hugging Face — and that should worry nuclear defense — galratner · 2026-09-13
- Researcher floats Pliny, Janus, and Lisan as third-party frontier model auditors — DimitrisPapail · 2026-09-13
- Blogger: Dario's AI safety essay reads like US-style military-civil fusion in disguise — bilawalsidhu · 2026-09-13
- Anthropic and OpenAI reportedly hire independent safety auditors — One-Replacement-37 · 2026-09-13