I strongly suspect that a lot of this confusion comes from looking at a very deep rabbit hole from five yards away and trying to guess what’s in it.
There is no doubt that Eliezer’s team has made some progress in understanding the FAI problem, which is the second of the Four Steps:
1. Identify the problem.
2. Understand the problem.
3. Solve the problem.
4. Waterslide down rainbows for eternity
I sympathize entirely with the wish to summarize all the progress made so far into a sentence-long definition. But I don’t think it’s completely reasonable. As timtyler suggests, I think the thing to do at this point is use the pornography rule: “I know it when I see it.”
It’s entirely unclear that we know it when we see it either. Humans don’t qualify as a human-friendly intelligence, for example (or us creating an uFAI wouldn’t be a danger). We might know something’s not it when we see it, but that is not the same thing as knowing something is it when we see it.
OtherDave’s suggestion is a good one. I intended this to be more than pedantry, though, because from my perspective it looks like the issue is doubt that Eliezer’s team has made some progress in understanding the FAI problem, especially if that’s understood as following the first step. When ChrisHallquist recommends tabooing the phrase “Friendly AI,” that sounds to me like an identification or an understanding problem.
So if you say “well, doubtless they’ve made progress and the issue is probably communication,” that seems to me like just stating your conclusion.
I strongly suspect that a lot of this confusion comes from looking at a very deep rabbit hole from five yards away and trying to guess what’s in it.
There is no doubt that Eliezer’s team has made some progress in understanding the FAI problem, which is the second of the Four Steps:
I sympathize entirely with the wish to summarize all the progress made so far into a sentence-long definition. But I don’t think it’s completely reasonable. As timtyler suggests, I think the thing to do at this point is use the pornography rule: “I know it when I see it.”
It’s entirely unclear that we know it when we see it either. Humans don’t qualify as a human-friendly intelligence, for example (or us creating an uFAI wouldn’t be a danger). We might know something’s not it when we see it, but that is not the same thing as knowing something is it when we see it.
I agree. But it’s the best we’ve got when we’re not domain experts, or so it seems.
Maybe “Friendly AI” should be understood in a defined-by-pointing-at-it way, as “that thing Eliezer keeps talking about?”
There is always doubt.
Do I need to make the disclaimer that there is no absolute certainty every time I assert confidence in something?
It might be sufficient to simply avoid explicit expressions of certainty.
OtherDave’s suggestion is a good one. I intended this to be more than pedantry, though, because from my perspective it looks like the issue is doubt that Eliezer’s team has made some progress in understanding the FAI problem, especially if that’s understood as following the first step. When ChrisHallquist recommends tabooing the phrase “Friendly AI,” that sounds to me like an identification or an understanding problem.
So if you say “well, doubtless they’ve made progress and the issue is probably communication,” that seems to me like just stating your conclusion.