Tag

#AI-safety

1 article tagged with #AI-safety.

AI Alignment Riset dan teknik untuk memastikan AI berperilaku sesuai dengan nilai dan niat manusia. Termasuk RLHF, Constitutional AI, scalable oversight, interpretability. concepts · June 21, 2026

Type at least 2 characters to search.

Press ↑ ↓ to navigate, ↵ to open, esc to close.