Sounds good. I sort of feel obligated to point out that CEV is about policy, public relations, and abstract philosophy significantly more than it is about the real problem of FAI. Thus I'm a little worried about what "working on CEV" might look like if the optimization targets aren't very clear from the start.
Bringing CEV up-to-date and ideally emphasizing that whatever line of reasoning you are using to object to some imagined CEV scenario, because that line of reasoning is contained within you, CEV will by its very nature also take into account that line of reasoning sounds more straight-forwardly good. (Actually, Steve had some analysis about why even smart people so consistently miss this point (besides the typical diagnosis of 'insufficient Hofstadter during adolescence syndrome') which should really go into a future CEV doc. A huge part of the common confusion about CEV is due to people not really noticing or understanding the whole "if you can think of a failure mode, the AI can think of it" thing.)
whatever line of reasoning you are using to object to some imagined CEV scenario, because that line of reasoning is contained within you, CEV will by its very nature also take into account that line of reasoning
This assumes that CEV actually works as intended (and the intention was the right one), which would be exactly the question under discussion (hopefully), so in that context you aren't allowed to make that assumption.
The adequate response is not that it's "correct by definition" (because it isn't, it's a constructed artifact that could ...
I've been working on metaethics/CEV research for a couple months now (publishing mostly prerequisite material) and figured I'd share some of the sources I've been using.
CEV sources.
Motivation. CEV extrapolates human motivations/desires/values/volition. As such, it will help to understand how human motivation works.
Extrapolation. Is it plausible to think that some kind of extrapolation of human motivations will converge on a single motivational set? How would extrapolation work, exactly?
Metaethics. Should we use CEV, or something else? What does 'should' mean?
Building the utility function. How can a seed AI be built? How can it read what to value?
Preserving the utility function. How can the motivations we put into a superintelligence be preserved over time and self-modifcation?
Reflective decision theory. Current decision theories tell us little about software agents that make decisions to modify their own decision-making mechanisms.
Additional suggestions welcome. I'll try to keep this page up-to-date.