Two grounded scenarios: closed-weight bioweapon and open-weight cyberattack

StephenLCasper · x · 2026-10-20

Thread follow-up: the paper outlines two grounded illustrative scenarios — (1) a non-state group, a closed-weight model, and a biological attack; (2) a state-sponsored group, an open-weight model, and a cyberattack.

Related event: Harvard Belfer Paper Warns First Major AI-Enabled Terror Attack Could Come as Early as 2027-2028(10 posts)→

Original post →

More from Safety

• Vals AI: DeepSeek V4.1 Flash beats GPT 6 Sol on offensive cyber benchmark, open weights favor defenders — sayashk · 2026-10-21
• Joshua Saxe: Curb AI cyber misuse without blocking open weights — joshua_saxe · 2026-10-21
• What rules would you need to trust an agent with write access? A builder's draft framework — Fresh_Spread_9223 · 2026-10-21
• WhatsApp Hid Instructions in Help Pages Telling Its AI Chatbot Not to Recommend Privacy Regulators — evilsocket · 2026-10-20
• Ex-OpenAI policy chief blasts OpenAI's retreat from AI chip controls to appease Nvidia — Miles_Brundage · 2026-10-20
• Time for Guardrails on Government Too: Rethinking Who AI Policy Constrains — neil_chilson · 2026-10-20

Safety channel →