AI Alignment
المحاذاة
تحدي ضمان أن تتصرف أنظمة الذكاء الاصطناعي وفقاً لقيم البشر وأهدافهم ونواياهم، وهو أحد أبرز مسائل سلامة الذكاء الاصطناعي.
The challenge of ensuring AI systems behave in accordance with human values, goals, and intentions — one of the central problems in AI safety.
Also translated asمحاذاة الذكاء الاصطناعي، مواءمة الذكاء الاصطناعي
First appears in this corpus in: Deep Reinforcement Learning from Human Preferences (2017)
Appears in these papers
- Deep Reinforcement Learning from Human Preferences2017in the sky ✦
- Are Emergent Abilities of Large Language Models a Mirage?2023in the sky ✦
- The Falcon Series of Open Language Models2023in the sky ✦
- Llama 2: Open Foundation and Fine-Tuned Chat Models2023in the sky ✦
- RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback2023in the sky ✦