There are two forms of AI in my book and either one contains risk. The learned AI or the AI that comes with complete knowledge. to involve AI in risk assesment you will need the AI in the wilderness with nothing held back. Truly though would you do that to AI? Kind of like shoving all information down the brain of a 13 year old girl. She would just go berserk and will become defiant in the end.
The best alternative safe AI that contains no risk is the copied brain of a scientist.
Why does SI/LW focus so much on AI-FOOM disaster, with apparently much less concern for things like
Why, for example, is lukeprog's strategy sequence titled "AI Risk and Opportunity", instead of "The Singularity, Risks and Opportunities"? Doesn't it seem strange to assume that both the risks and opportunities must be AI related, before the analysis even begins? Given our current state of knowledge, I don't see how we can make such conclusions with any confidence even after a thorough analysis.
SI/LW sometimes gives the impression of being a doomsday cult, and it would help if we didn't concentrate so much on a particular doomsday scenario. (Are there any doomsday cults that say "doom is probably coming, we're not sure how but here are some likely possibilities"?)