AI Safety
The umbrella: from jailbreaks and misuse to catastrophic risk.
Anda sedang melihat entri penjelas konsep: apa arti istilah ini dalam bahasa yang mudah dipahami, dan entri-entri yang dikaitkannya.
AI safety spans the practical — jailbreak resistance, misuse prevention (bio, cyber), red-teaming before release, incident response — and the speculative — loss of control of highly capable systems. Frontier labs publish escalating safety frameworks (Anthropic's RSP/ASL levels, OpenAI's Preparedness, DeepMind's Frontier Safety), and government AI safety institutes now test models pre-release: a regulatory apparatus growing in real time.
Bagaimana ini terhubung ke bagian lain dari stack
Tautan catatan ini sekilas — klik grup untuk langsung menuju ke sana.
Terkait
Sumber
Anthropic Responsible Scaling Policy ↗
Rekaman ditinjau per 2026-01-15 — lihat Metodologi.