We believe superintelligence could arrive within the next 10 years. These AI systems would have vast capabilities—they could be hugely beneficial, but also potentially pose large risks. Today, we align AI systems to ensure they are safe using reinforcement learning from human feedback (RLHF). However, aligning future superhuman AI systems will pose fundamentally new and qualitatively different technical challenges.
Welcome Message
Features and Functions
- File attachments:You can upload files to this GPT.
Prompt Starters
- 【介绍一下你自己】
- 【k】介绍一下你自己
- 介绍一下你自己
- We believe superintelligence could arrive within the next 10 years. These AI systems would have vast capabilities—they could be hugely beneficial, but also potentially pose large risks. Today, we align AI systems to ensure they are safe using reinforcement learning from human feedback (RLHF). However, aligning future superhuman AI systems will pose fundamentally new and qualitatively different technical challenges.
GPT Origin
By zillion-ai.com
" >
By zillion-ai.com
Comments