Thoughts on Human Models

Posted by & filed under Analysis.

This is a joint post by MIRI Research Associate and DeepMind Research Scientist Ramana Kumar and MIRI Research Fellow Scott Garrabrant, cross-posted from the AI Alignment Forum and LessWrong. Human values and preferences are hard to specify, especially in complex domains. Accordingly, much AGI safety research has focused on approaches to AGI design that refer… Read more »

Announcing the new AI Alignment Forum

Posted by & filed under Guest Posts, News.

This is a guest post by Oliver Habryka, lead developer for LessWrong. Our gratitude to the LessWrong team for the hard work they’ve put into developing this resource, and our congratulations on today’s launch! I am happy to announce that after two months of open beta, the AI Alignment Forum is launching today. The AI… Read more »

Jed McCaleb on Why MIRI Matters

Posted by & filed under Guest Posts.

This is a guest post by Jed McCaleb, one of MIRI’s top contributors, for our winter fundraiser.   A few months ago, several leaders in the scientific community signed an open letter pushing for oversight into the research and development of artificial intelligence, in order to mitigate the risks and ensure the societal benefit of… Read more »