I don’t think Eliezer claimed there is a perfect abstract one-place function of morality somewhere. From what I understood of this Sequence, he claimed that :
Morality is mostly what an algorithm feels from inside, the application of an algorithm to data, that unfolds in different ways in many different situations. The algorithm is different from people to people, it is a 2-place function.
Your morality can’t come from nowhere, you can’t teach morality to a “perfect philosopher of total emptiness” nor to a rock. The foundations of morality, the bootstrapping of it, comes from evolution and feelings/abilities/goals generated by it. Your morality can change, but you’ll have to use your previous morality to evaluate change to do to itself.
The algorithms of two humans are very close to each other, much more than the morality of pebblesorters or paper-clip optimizers. Most moral disagreements between humans come from different ways of unfolding the algorithm, due to biases, missing informations, failure to use common skills like empathy, different expectations about consequences… not because of the differences between terminal values.
It’s hard to summarize the work of another, and to summarize so many posts in 3 simple points, so don’t hesitate to correct me if I misrepresented Eliezer’s position. But that’s how I understood it, and so far I agree with it.
2) Yes. Your values change based on your current values. One issue I hadn’t brought up is that I believe your moral values are only some of your values, and do not solely determine your choices.
3) I don’t think the algorithms are that close. Along the lines of research of Jonathan Haidt, I think there are different morality pattern match algorithms along the axes of fairness, autonomy, disgust, etc. I would guess that the algorithms for each axis are similar, but the weighting between them is less similar, as borne out in Haidt’s work.
Also, when you say “unfolding the algorithm”, what does that mean, and what algorithm are you speaking of? My unfolding of my 2place algorithm?
My largest issue is the implication that our 2place functions are imperfect images of an ideal 1place function. In some places that’s the clear implication I take, and in others, it’s not. In his final summary, he explicitly says:
we are dereferencing two different pointers to the same unverbalizable abstract computation.
I think that’s just wrong. We’re using the same label, but dereferencing to different 2place functions, mine and yours, and that’s why we’re often talking at cross purposes and don’t make much progress.
Eliezer says that we end up where we started, arguing in the same way we always have. I think we should be arguing in a new way. No longer trying to bludgeon people into submission to the values of our own 2place function, mistaking it for a universal 1place function, but trying to understand the other guy’s 2place function, and appealing to that.
I think I disagree with you, but I’m not sure exactly what you mean by what you’re saying. It might help to answer these questions three:
Taboo “universal”. What do you mean by “universal 1-place function”?
In what sense do you think morality is a 2-place function? How is this function applied in decision making? Does that mean it would be wrong to stop people whose “morality” says torture is “good” from torturing people?
In what sense do you think this 2-place function is different between people? (I’m looking for a precise answer in terms of the first and second argument to the function here.)
I don’t think Eliezer claimed there is a perfect abstract one-place function of morality somewhere. From what I understood of this Sequence, he claimed that :
Morality is mostly what an algorithm feels from inside, the application of an algorithm to data, that unfolds in different ways in many different situations. The algorithm is different from people to people, it is a 2-place function.
Your morality can’t come from nowhere, you can’t teach morality to a “perfect philosopher of total emptiness” nor to a rock. The foundations of morality, the bootstrapping of it, comes from evolution and feelings/abilities/goals generated by it. Your morality can change, but you’ll have to use your previous morality to evaluate change to do to itself.
The algorithms of two humans are very close to each other, much more than the morality of pebblesorters or paper-clip optimizers. Most moral disagreements between humans come from different ways of unfolding the algorithm, due to biases, missing informations, failure to use common skills like empathy, different expectations about consequences… not because of the differences between terminal values.
It’s hard to summarize the work of another, and to summarize so many posts in 3 simple points, so don’t hesitate to correct me if I misrepresented Eliezer’s position. But that’s how I understood it, and so far I agree with it.
1) Yes. Different between two people.
2) Yes. Your values change based on your current values. One issue I hadn’t brought up is that I believe your moral values are only some of your values, and do not solely determine your choices.
3) I don’t think the algorithms are that close. Along the lines of research of Jonathan Haidt, I think there are different morality pattern match algorithms along the axes of fairness, autonomy, disgust, etc. I would guess that the algorithms for each axis are similar, but the weighting between them is less similar, as borne out in Haidt’s work.
Also, when you say “unfolding the algorithm”, what does that mean, and what algorithm are you speaking of? My unfolding of my 2place algorithm?
My largest issue is the implication that our 2place functions are imperfect images of an ideal 1place function. In some places that’s the clear implication I take, and in others, it’s not. In his final summary, he explicitly says:
I think that’s just wrong. We’re using the same label, but dereferencing to different 2place functions, mine and yours, and that’s why we’re often talking at cross purposes and don’t make much progress.
Eliezer says that we end up where we started, arguing in the same way we always have. I think we should be arguing in a new way. No longer trying to bludgeon people into submission to the values of our own 2place function, mistaking it for a universal 1place function, but trying to understand the other guy’s 2place function, and appealing to that.
I think I disagree with you, but I’m not sure exactly what you mean by what you’re saying. It might help to answer these questions three:
Taboo “universal”. What do you mean by “universal 1-place function”?
In what sense do you think morality is a 2-place function? How is this function applied in decision making? Does that mean it would be wrong to stop people whose “morality” says torture is “good” from torturing people?
In what sense do you think this 2-place function is different between people? (I’m looking for a precise answer in terms of the first and second argument to the function here.)