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 Can we safely automate alignment research? - Joe Carlsmith
\|	\|	www.lesswrong.com Can we safely automate alignment research? - LessWrong	0.0 parsecs away Travel
\|	\|	It's really important; we have a real shot; there are a lot of ways to fail.	0.0 parsecs away Travel
\|	\|	www.lesswrong.com Anthropic: Core Views on AI Safety: When, Why, What, and How - LessWrong	1.4 parsecs away Travel
\|	\|	We founded Anthropic because we believe the impact of AI might be comparable to that of the industrial and scientific revolutions, but we aren't conf...	1.4 parsecs away Travel
\|	\|	www.lesswrong.com Empirical work that might shed light on scheming (Section 6 of "Scheming AIs") - LessWrong	2.8 parsecs away Travel
\|	\|	This is Section 6 of "Scheming AIs."	2.8 parsecs away Travel
\|	\|	www.lesswrong.com AI as a science, and three obstacles to alignment strategies - LessWrong	30.9 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. ...	30.9 parsecs away Travel