As promised, here is the "Q" part of the Less Wrong Video Q&A with Eliezer Yudkowsky.
The Rules
1) One question per comment (to allow voting to carry more information about people's preferences).
2) Try to be as clear and concise as possible. If your question can't be condensed to a few paragraphs, you should probably ask in a separate post. Make sure you have an actual question somewhere in there (you can bold it to make it easier to scan).
3) Eliezer hasn't been subpoenaed. He will simply ignore the questions he doesn't want to answer, even if they somehow received 3^^^3 votes.
4) If you reference certain things that are online in your question, provide a link.
5) This thread will be open to questions and votes for at least 7 days. After that, it is up to Eliezer to decide when the best time to film his answers will be. [Update: Today, November 18, marks the 7th day since this thread was posted. If you haven't already done so, now would be a good time to review the questions and vote for your favorites.]
Suggestions
Don't limit yourself to things that have been mentioned on OB/LW. I expect that this will be the majority of questions, but you shouldn't feel limited to these topics. I've always found that a wide variety of topics makes a Q&A more interesting. If you're uncertain, ask anyway and let the voting sort out the wheat from the chaff.
It's okay to attempt humor (but good luck, it's a tough crowd).
If a discussion breaks out about a question (f.ex. to ask for clarifications) and the original poster decides to modify the question, the top level comment should be updated with the modified question (make it easy to find your question, don't have the latest version buried in a long thread).
Update: Eliezer's video answers to 30 questions from this thread can be found here.
"Just think of nuclear espionage and of the kind of security that surrounds the development of military and intelligence hardware and software."
The reason the idea of the nuclear chain reaction was kept secret, was because one man named Leo Szilard realized the damage it could do, and had his patent for the idea classified as a military secret. It wasn't kept secret by default; if it weren't for Szilard, it would probably have been published in physics journals like every other cool new idea about atoms, and the Nazis might well have gotten nukes before we did.
"If you're building something that could overthrow all the power structures in the world, it would be surprising if nobody tried to spy on you (or worse; kill you, derail the project, steal the almost finished code, etc)."
Only if they believe you, which they almost certainly won't. Even in the (unlikely) case that someone thought that an AI taking over the world was realistic, there's still an additional burden of proof on top of that, because they'd also have to believe that SIAI is competent enough to have a decent shot at pulling it off, in a field where so many others have failed.
So you're saying SIAI is deliberately appearing incompetent and far from its goal to avoid being attacked?
ETA: I realize you're probably not saying it's doing that already, but you certainly suggest that it's going to be in SIAI's best interests going forward.