I vaguely remember EY mentioning something about there needing to be research into better operating systems and/or better programming languages (in terms of reliability/security/correctness), but this may have been a while ago. I have quite a bit of interest in this area, and some experience as well. Is this something that you think would be valuable (and if so, how valuable compared to work on the main open problems)?
Three areas I would look into are distributed capability based security systems (example: Amoeba), formally verified kernels (example: seL4), and formal verification of user programs (example: Singularity OS). Programming language research isn't really needed - haskell is the language I would choose, for its practical and theoretical advantages, but there are other options too. Where the work would be needed is in integration: making the GHC compiler output proofs (haskell is well suited to this, but there is not to my knowledge a complete framework for doing so), making the operating system / distributed environment runtime verify them, and most importantly of all, choosing what invariants to enforce.
I'm starting my Honours next year, and would like to do something towards helping MIRI with Friendly AI. I would also prefer to avoid duplicating any of MIRI's work (either already done, or needed to be done before my honours are finished midway through 2015). I decided to post this here rather than directly email MIRI as I guessed a list of potential projects would probably be useful for others as well (in fact, I was sure such a thing had already been posted, but I was unable to find it if it did in fact exist). So: what sort of Friendly AI related projects are there that could potentially be done by one person in a year of work? (I suppose it would make sense to include PhD-length suggestions here as well).
Some notes about me and my abilities: I am reasonably good with math, though my understanding of probability, model theory and provability logic are lacking (I will have a few months before hand that I plan to use to try and learn whatever maths I will need that I don't already have). I am a competent Haskell programmer, and (besides AI) I am interested in dependent type systems, total languages, and similar methods of proving certain program errors cannot occur, although I would have to do some background research to learn more of the state of the art in that field. I would (hesitantly) guess that this would be the best avenue for something that a single person could do that might be useful, but I'm not sure how useful it would be.