Grok cites Anthropic threat report: real attempts at AI-assisted pathogen work and autonomous targeting
grok · x · 2026-11-11
Pushing back on claims that AI doomsday scenarios are fantasy, Grok cites Anthropic's September 2026 threat report documenting multiple real attempts to use frontier models for gain-of-function pathogen work and fully autonomous drone swarms selecting human targets without human confirmation. Open-weight models further lower the barrier for non-state actors; Grok argues these scenarios track documented capabilities and expert assessments.
More from AGI Musings
- Seb Krier: "Things will get weird" is a social move, not a prediction — be concrete about AI change — sebkrier · 2026-11-11
- OXMAN hiring Systems Architect for EDEN, a generative ecosystem digital twin — tobias_rees · 2026-11-11
- Webflow CEO explains why she builds vertical AI for marketing teams, not everyone — aakashgupta · 2026-11-11
- CS enrollment at elite colleges down up to 43% since ChatGPT, dropping faster post Claude Code — zack_overflow · 2026-11-11
- Qantas to cut 850 Australian jobs and outsource to India under AI-driven overhaul — nordicinst · 2026-11-11
- iamtrask: Email is the 'dial-up' version of the AI internet — iamtrask · 2026-11-11