Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		joecarlsmith.com AI for AI safety - Joe Carlsmith
\|	\|	www.lesswrong.com An open letter to SERI MATS program organisers - LessWrong	2.7 parsecs away Travel
\|	\|	(Independent) alignment researchers need to be exceptionally good at philosophy of science In order to be effective, independent AI alignment/safety/...	2.7 parsecs away Travel
\|	\|	www.greaterwrong.com Role Architectures: Applying LLMs to consequential tasks - LessWrong 2.0 viewer	3.1 parsecs away Travel
\|	\|	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.	3.1 parsecs away Travel
\|	\|	www.alignmentforum.org Perform Tractable Research While Avoiding Capabilities Externalities [Pragmatic AI Safety #4] - AI Alignment Forum	2.5 parsecs away Travel
\|	\|	This is the fourth post in a sequence of posts that describe our models for Pragmatic AI Safety. ...	2.5 parsecs away Travel
\|	\|	rationallyspeaking.blogspot.com Rationally Speaking: You don't really exist, do you?	23.8 parsecs away Travel
\|		by Massimo Pigliucci www.universaltheory.org For some time I have been noticing the emergence of a strange trinity of beliefs am...	23.8 parsecs away Travel