AI Safety
The umbrella: from jailbreaks and misuse to catastrophic risk.
Stai visualizzando una scheda concettuale: cosa significa questo termine in linguaggio chiaro, e i record che mette in relazione.
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.
Come si collega al resto dello stack
I collegamenti di questa scheda a colpo d'occhio — clicca un gruppo per raggiungerlo.
Correlati
Fonti
Anthropic Responsible Scaling Policy ↗
Record revisionato al 2026-01-15 — vedi Metodologia.