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		www.alignmentforum.org Risks from Learned Optimization: Introduction - AI Alignment Forum
\|	\|	www.lesswrong.com Risks from Learned Optimization: Introduction - LessWrong	0.0 parsecs away Travel
\|	\|	AI researchers warn that advanced machine learning systems may develop their own internal goals that don't match what we intended. This "mesa-optimiz...	0.0 parsecs away Travel
\|	\|	www.lesswrong.com AI as a science, and three obstacles to alignment strategies - LessWrong	2.3 parsecs away Travel
\|	\|	AI used to be a science. In the old days (back when AI didn't work very well), people were attempting to develop a working theory of cognition. ...	2.3 parsecs away Travel
\|	\|	www.lesswrong.com Thoughts on "AI is easy to control" by Pope & Belrose - LessWrong	3.4 parsecs away Travel
\|	\|	Quintin Pope & Nora Belrose have a new"AI Optimists" website, along with a new essay "AI is easy to control", arguing that the risk of human extinct...	3.4 parsecs away Travel
\|	\|	www.screendoorpartners.com Screendoor Blog \| Screendoor Update: First Convening, Two New Investments, and Preparing for Growth	14.3 parsecs away Travel
\|		[AI summary] Screendoor highlights its first in-person convening of emerging venture capital managers and institutional investors, announces new investments, and discusses future growth plans and commitment to supporting underrepresented founders in tech.	14.3 parsecs away Travel