I definitely agree with your first paragraph (and thanks for the tip on SIAI vs SI). The only caveat is if evolved/brain-based/black-box AGI is several orders of magnitude easier to create than an AGI with a more modular architecture where SI's safety research can apply, that's a big problem.
On the second point, what you say makes sense. Particularly, AGI feelings haven't been completely ignored at LW; if they prove important, SI doesn't have anything against incorporating them into safety research; and AGI feelings may not be material to AGI behavior anyway.
However, I still do think that an ability to tell what feelings an AGI is experiencing-- or more generally, being able to look at any physical process and being able to derive what emotions/qualia are associated with it-- will be critical. I call this a "qualia translation function".
Leaving aside the ethical imperatives to create such a function (which I do find significant-- the suffering of not-quite-good-enough-to-be-sane AGI prototypes will probably be massive as we move forward, and it behooves us to know when we're causing pain), I'm quite concerned about leaky reward signal abstractions.
I imagine a hugely-complex AGI executing some hugely-complex decision process. The decision code has been checked by Very Smart People and it looks solid. However, it just so happens that whenever it creates a cat it (internally, privately) feels the equivalent of an orgasm. Will that influence/leak into its behavior? Not if it's coded perfectly. However, if something of its complexity was created by humans, I think the chance of it being coded perfectly is Vanishingly small. We might end up with more cats than we bargained for. Our models of the safety and stability dynamic of an AGI should probably take its emotions/qualia into account. So I think all FAI programmes really would benefit from such a "qualia translation function".
I agree that, in order for me to behave ethically with respect to the AGI, I need to know whether the AGI is experiencing various morally relevant states, such as pain or fear or joy or what-have-you. And, as you say, this is also true about other physical systems besides AGIs; if monkeys or dolphins or dogs or mice or bacteria or thermostats have morally relevant states, then in order to behave ethically it's important to know that as well. (It may also be relevant for non-physical systems.)
I'm a little wary of referring to those morally relevant states a...
If you've recently joined the Less Wrong community, please leave a comment here and introduce yourself. We'd love to know who you are, what you're doing, what you value, how you came to identify as a rationalist or how you found us. You can skip right to that if you like; the rest of this post consists of a few things you might find helpful. More can be found at the FAQ.
A few notes about the site mechanics
A few notes about the community
If English is not your first language, don't let that make you afraid to post or comment. You can get English help on Discussion- or Main-level posts by sending a PM to one of the following users (use the "send message" link on the upper right of their user page). Either put the text of the post in the PM, or just say that you'd like English help and you'll get a response with an email address.
* Normal_Anomaly
* Randaly
* shokwave
* Barry Cotter
A note for theists: you will find the Less Wrong community to be predominantly atheist, though not completely so, and most of us are genuinely respectful of religious people who keep the usual community norms. It's worth saying that we might think religion is off-topic in some places where you think it's on-topic, so be thoughtful about where and how you start explicitly talking about it; some of us are happy to talk about religion, some of us aren't interested. Bear in mind that many of us really, truly have given full consideration to theistic claims and found them to be false, so starting with the most common arguments is pretty likely just to annoy people. Anyhow, it's absolutely OK to mention that you're religious in your welcome post and to invite a discussion there.
A list of some posts that are pretty awesome
I recommend the major sequences to everybody, but I realize how daunting they look at first. So for purposes of immediate gratification, the following posts are particularly interesting/illuminating/provocative and don't require any previous reading:
More suggestions are welcome! Or just check out the top-rated posts from the history of Less Wrong. Most posts at +50 or more are well worth your time.
Welcome to Less Wrong, and we look forward to hearing from you throughout the site.