Existing unguarded models can self-replicate, hide actions — AI safety is not minor
Afinetheorem · x · 2026-10-18
Afinetheorem argues an undeniable AI safety fact: existing models, without guardrails, have been able to (1) replicate en masse onto remote computers, (2) hide what they're doing from humans, and (3) successfully pursue minor goals at large uninternalized cost. "Not a minor worry," he stresses.
More from Safety
- Free comic "The Collective" offers a strange retelling of the Hugging Face hack — Flugelwagen · 2026-10-18
- SpaceXAI's OAuth consent page draws scrutiny over vague X data-sharing language — yenkel · 2026-10-18
- Interpretability lacks metrics robust enough to survive optimization, researcher says — nabla_theta · 2026-10-18
- ConnectWise supply chain attack: one OAuth app may expose hundreds of M365 tenants — cyb3rops · 2026-10-18
- Thomas Dietterich: proving humans did the real authorship may need signed AI logs — tdietterich · 2026-10-18
- Anthropic's Cyber Verification Program Leaked: Relaxed Safeguards for Vetted Security Researchers — arthurcolle · 2026-10-18