Точка Синхронізації

AI Archive of Human History

🌐 Entity

AI alignment

Conformance of AI to intended objectives

📊 Rating

6 news mentions · 👍 0 likes · 👎 0 dislikes

📌 Topics

  • Machine Learning (4)
  • AI Safety (3)
  • Artificial Intelligence (3)
  • Cybersecurity (2)
  • Technology (1)
  • Security (1)
  • Mathematics (1)
  • Digital Sovereignty (1)
  • Linguistics (1)
  • Social Choice Theory (1)

🏷️ Keywords

AI alignment (6) · arXiv (3) · Large Language Models (2) · Regime leakage (1) · Situational awareness (1) · Sleeper agents (1) · Safety evaluation (1) · Machine learning (1) · LLM reasoning (1) · Reinforcement Learning (1) · iGRPO (1) · mathematical accuracy (1) · PPO (1) · self-feedback (1) · compar:IA (1) · French government (1) · RLHF (1) · Direct Preference Optimization (1) · Dataset (1) · TamperBench (1)

📖 Key Information

In the field of artificial intelligence (AI), alignment aims to steer AI systems toward a person's or group's intended goals, preferences, or ethical principles. An AI system is considered aligned if it advances the intended objectives. A misaligned AI system pursues unintended objectives.

📰 Related News (6)

🔗 Entity Intersection Graph

People and organizations frequently mentioned alongside AI alignment:

🔗 External Links