But still, in most cases I’d prefer to learn the actual evidence that someone saw, rather than their posterior beliefs or even their likelihood ratios (as your conversation with Hal Finney here shows very nicely).
I think that makes sense (and made the point more explicitly at the end of Probability Space & Aumann Agreement). But sharing evidence is pretty costly and it’s infeasible to share everything that goes into one’s posterior beliefs. It seems sensible to share posterior beliefs first and then engage in some protocol (e.g., double cruxing or just ordinary discussion) for exchanging the most important evidence while minimizing cost with whoever actually disagrees with you. (This does leave the possibility that two people agree after having observed different evidence and could still benefit from exchanging evidence, but still seems reasonable as a rule of thumb in the real world.)
And when sharing evidence you don’t have to qualify it so much, you can just say what you saw.
I think you still do? Because you may not be sure that you remember it correctly, or interpreted it correctly in the first place, or don’t totally trust the source of the evidence, etc.
That’s fair. Though I’m also worried that when Alice and Bob exchange beliefs (“I believe in global warming” “I don’t”), they might not go on to exchange evidence, because one or both of them just get frustrated and leave. When someone states their belief first, it’s hard to know where to even start arguing. This effect is kind of unseen, but I think it stops a lot of good conversations from happening.
While if you start with evidence, there’s at least some chance of conversation about the actual thing. And it’s not that time-consuming, if everyone shares their strongest evidence first and gets a chance to respond to the other person’s strongest evidence. I wish more conversations went like that.
I think that makes sense (and made the point more explicitly at the end of Probability Space & Aumann Agreement). But sharing evidence is pretty costly and it’s infeasible to share everything that goes into one’s posterior beliefs. It seems sensible to share posterior beliefs first and then engage in some protocol (e.g., double cruxing or just ordinary discussion) for exchanging the most important evidence while minimizing cost with whoever actually disagrees with you. (This does leave the possibility that two people agree after having observed different evidence and could still benefit from exchanging evidence, but still seems reasonable as a rule of thumb in the real world.)
I think you still do? Because you may not be sure that you remember it correctly, or interpreted it correctly in the first place, or don’t totally trust the source of the evidence, etc.
That’s fair. Though I’m also worried that when Alice and Bob exchange beliefs (“I believe in global warming” “I don’t”), they might not go on to exchange evidence, because one or both of them just get frustrated and leave. When someone states their belief first, it’s hard to know where to even start arguing. This effect is kind of unseen, but I think it stops a lot of good conversations from happening.
While if you start with evidence, there’s at least some chance of conversation about the actual thing. And it’s not that time-consuming, if everyone shares their strongest evidence first and gets a chance to respond to the other person’s strongest evidence. I wish more conversations went like that.