New report: “Computable probability distributions which converge…”

Posted by & filed under News.

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 believing true Π1 sentences will disbelieve true Π2 sentences.” Abstract: It might seem reasonable that after seeing unboundedly many… Read more »

New report: “Toward Idealized Decision Theory”

Posted by & filed under News.

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 aligning smarter-than-human artificial systems with human interests. We discuss the shortcomings of two standard formulations of… Read more »

New report: “Tiling agents in causal graphs”

Posted by & filed under News.

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 similar to themselves while avoiding Gödelian diagonalization issues) in environments about which the agent can… Read more »

New paper: “Concept learning for safe autonomous AI”

Posted by & filed under News.

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 concepts such as well-being or rights. These concepts cannot be given an explicit formal definition,… Read more »

December newsletter

Posted by & filed under Newsletters.

  MIRI’s winter fundraising challenge has begun! Every donation made to MIRI between now and January 10th will be matched dollar-for-dollar, up to a total of $100,000!   Donate now to double your impact while helping us raise up to $200,000 (with matching) to fund our research program. Research Updates We’ve published a new guide… Read more »

2014 Winter Matching Challenge!

Posted by & filed under News.

Thanks to the generosity of Peter Thiel,1 every donation made to MIRI between now and January 10th will be matched dollar-for-dollar, up to a total of $100,000! $0 $25K $50K $75K $100K We have reached our matching total of $100,000! 83 Total Donors Now is your chance to double your impact while helping us raise up to… Read more »

Three misconceptions in Edge.org’s conversation on “The Myth of AI”

Posted by & filed under Analysis.

A recent Edge.org conversation — “The Myth of AI” — is framed in part as a discussion of points raised in Bostrom’s Superintelligence, and as a response to much-repeated comments by Elon Musk and Stephen Hawking that seem to have been heavily informed by Superintelligence. Unfortunately, some of the participants fall prey to common misconceptions about the standard case for AI as an existential risk, and… Read more »