Tech
[程序员] 如果 AI 能够判断“训练它的人定义错了”，它应该服从谁？
anthropic 对 z 国抱有如此敌意的情况下, 是否会把 claude 训练成 z 国用户抱有恶意的 AI, 实在是细思极恐
Read the full discussion on V2EX
This article was aggregated from V2EX. Click to join the conversation.
View on V2EX
Related Trends in Tech
🌍
The streamers are fighting over Halloween
🌍
Snap tries to make the case again for its $2,200 smart glasses
🌍
Your startup’s next teammate might be an AI agent: Gusto, Insight Partners, and Leland explain what that changes at TechCrunch Disrupt 2026
Self-Hosting a Dockerized App on WSL2, Exposed with a Cloudflare Tunnel
🌍
Why "Remove Background" Is the Wrong Mental Model for Video
I Built TGDown, a Chrome Extension for Downloading Telegram Web Media