Recently, MIRI released 7 brief technical reports that explain several pieces of theoretical progress made at our December 2013 research workshop. Several of these results build on work done at our July and November 2013 workshops, and also on between-workshop research by Paul Christiano, Benja Fallenstein, and others.
To understand these technical reports in context, and to discuss them, please see Benja Fallenstein’s post: Results from MIRI’s December workshop. See also two posts about the workshop by workshop participant John Baez.
The 7 technical reports are:
- Hahn, “Scientific Induction in Probabilistic Metamathematics“
- Yudkowsky, “The Procrastination Paradox“
- Fallenstein, “An infinitely descending sequence of sound theories each proving the next consistent“
- Soares, “Fallenstein’s Monster“
- Stiennon, “Recursively-defined logical theories are well-defined“
- Fallenstein, “The 5-and-10 problem and the tiling agents formalism“
- Fallenstein, “Decreasing mathematical strength in one formalization of parametric polymorphism“
Also, Nik Weaver attended the first day of the workshop, and gave a tutorial on his response paper to Yudkowsky & Herreshoff’s tiling agents paper, titled “Paradoxes of rational agency and formal systems that verify their own soundness.” Benja Fallenstein’s comments on Weaver’s idea of “naturalistic trust” are here: Naturalistic trust among AIs.