Explore >> Select a destination
|
You are here 
|
www.lesswrong.com | ||
| | | | |
distill.pub
|
|
| | | | | If we want to train AI to do what humans want, we need to study humans. | |
| | | | |
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. | |
| | | | |
scottaaronson.blog
|
|
| | | | | Update (Nov. 22): Theoretical computer scientist and longtime friend-of-the-blog Boaz Barak writes to tell me that, coincidentally, he and Ben Edelman just released a big essay advocating a version of "Reform AI Alignment" on Boaz's Windows on Theory blog, as well as on LessWrong. (I warned Boaz that, having taken the momentous step of posting... | |
| | | | |
pressron.wordpress.com
|
|
| | | Abstract: Machine and language models of computation differ so greatly in the computational complexity properties of their representation that they form two distinct classes that cannot be directly compared in a meaningful way. While machine models are self-contained, the properties of the language models indicate that they require a computationally powerful collaborator, and are better... | ||
