🔬

AGI架構藍圖

設計智能的未來!

🔬 立即試用

什麼是AGI?

為什麼重要?

🎯 模擬器提示

📚 術語表

AGI
通用人工智慧 - 在所有領域具有人類水平能力的人工智慧
ASI
人工超級智慧-人工智慧遠遠超越人類智能
ANI
狹義人工智慧 - 擅長特定任務的人工智慧(今天的人工智慧)
Alignment
確保人工智慧做人類真正想要的事情的挑戰
Singularity
人工智慧超越人類智慧並遞歸改進的假設點
IntelligenceExplosion
快速、遞歸的人工智慧自我改進
RLHF
根據人類回饋進行強化學習 - 根據人類偏好訓練人工智慧
ConstitutionalAI
訓練人工智慧遵循一系列原則
Interpretability
了解 AI 模型的內部運作原理
Corrigibility
AI允許自身被糾正的特性
InstrumentalConvergence
不同目標導致相似子目標的傾向
OrthogonalityThesis
智力和目標是獨立的
FLOPS
每秒浮點運算 - 運算能力的衡量標準

🎓 學習資源

💬 畀學習者嘅話

{'encouragement': "The future of AI is not yet written. By understanding AGI, you can help shape its development. This is humanity's most important challenge.", 'reminder': "You don't need a PhD to think about AI safety. The best ideas can come from anywhere. Your perspective matters.", 'action': 'Learn, discuss, question. Join communities working on AI safety. Every voice helps ensure AI benefits everyone.', 'dream': 'A researcher in Kenya might discover a key alignment insight. A student in Brazil might ask the question that prevents catastrophe. This work belongs to all of humanity.', 'wiaVision': 'WIA Pin Code believes the most important knowledge should be free. AGI will affect everyone - everyone deserves to understand it.'}

開始使用

免費,唔使註冊

開始使用 →