/explore
|
You are here 
|
www.lesswrong.com | ||
| | | | |
distill.pub
|
|
| | | | | If we want to train AI to do what humans want, we need to study humans. | |
| | | | |
nonzerosum.games
|
|
| | | | | Exploring the alignment of individual and collective interests in the realm of politics and society. | |
| | | | |
www.greaterwrong.com
|
|
| | | | | TL;DR:Strong problem-solving systems can be built from AI systems that play diverse roles, LLMs can readily play diverse roles in role architectures, and AI systems based on role architectures can be practical, safe, and effective in undertaking complex and consequential tasks. This article explores the practicalities and challenges of aligning large language models (LLMs[1]) to play central roles in performing tasks safely and effectively. It highlights the potential value of Open Agency and related role architectures in aligning AI for general applications while mitigating risks. | |
| | | | |
blogdial.wordpress.com
|
|
| | | It is clear that the State is not going to quietly disappear into the night, and leave everyone to live as free men. Given that they still feel the need to preserve the illusion that they have the consent of the governed, we can expect any technology that threatens the State to come under legislative... | ||
