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		blog.redwoodresearch.org What training data should developers filter to reduce risk from misaligned AI?
\|	\|	www.lesswrong.com AI safety techniques leveraging distillation - LessWrong	3.7 parsecs away Travel
\|	\|	It's currently possible to (mostly or fully) cheaply reproduce the performance of a model by training another (initially weaker) model to imitate the...	3.7 parsecs away Travel
\|	\|	www.alignmentforum.org Should AI Developers Remove Discussion of AI Misalignment from AI Training Data? - AI Alignment Forum	0.5 parsecs away Travel
\|	\|	There is some concern that training AI systems on content predicting AI misalignment will hyperstition AI systems into misalignment. This has been di...	0.5 parsecs away Travel
\|	\|	www.alignmentforum.org Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research - AI Alignment Forum	2.9 parsecs away Travel
\|	\|	Evan et al argue for developing "model organisms of misalignment" - AI systems deliberately designed to exhibit concerning behaviors like deception o...	2.9 parsecs away Travel
\|	\|	codeincomplete.com AI, ML, and Large Language Models \| Jake Gordon	33.1 parsecs away Travel
\|		Personal Website for Jake Gordon	33.1 parsecs away Travel