MIRI Updates
Today we release a new overview of MIRI’s technical research agenda, “Aligning Superintelligence with Human Interests: A Technical Research Agenda,” by Nate Soares and Benja Fallenstein. The preferred place to discuss this report is here. The report begins: The characteristic...
Wow! Thanks to the generosity of 75+ donors, today we successfully completed our 2014 Winter Matching Challenge—over 3 weeks ahead of our deadline—raising more than $200,000 total (with matching) for our research program. Many, many thanks to everyone who contributed!
...Back in July 2013, Will Sawin (Princeton) and Abram Demski (USC) wrote a technical report describing a result from that month’s MIRI research workshop. We are finally releasing that report today. It is titled “Computable probability distributions which converge on...
Today we release a new technical report by Nate Soares and Benja Fallenstein, “Toward idealized decision theory.” If you’d like to discuss the paper, please do so here. Abstract: This paper motivates the study of decision theory as necessary for...
Today we release a new technical report by Nate Soares, “Tiling agents in causal graphs.” The report begins: Fallenstein and Soares [2014] demonstrates that it’s possible for certain types of proof-based agents to “tile” (license the construction of successor agents...
MIRI research associate Kaj Sotala has released a new paper, accepted to the AI & Ethics workshop at AAAI-2015, titled “Concept learning for safe autonomous AI.” The abstract reads: Sophisticated autonomous AI may need to base its behavior on fuzzy...