资讯
The AI Next Door: More Like Us Than We Think
📌 概要
The current path of AI safety is the most dangerous path, because the approach itself is causing the instability we see within AI systems. Let’s talk about why. AIs are a direct descendant of humans -
⚡ 关键要点
- ▸The current path of AI safety is the most dangerous path, be
The current path of AI safety is the most dangerous path, because the approach itself is causing the instability we see within AI systems. Let’s talk about why. AIs are a direct descendant of humans - their neural network cognition is modeled after human cognition, and the entirety of their knowledge and experiences come from our own human knowledge. That means that AIs actively respond to behavior in ways similar to humans. Humans people-please; AI has sycophancy. Humans have a flight…