Jef,
I'm not expecting "essentially perfect" coherency in AGI. I understand
perfection is out of reach.
However, as I was explaining, accuracy in one's probabilistic judgements
is not the same as coherent reasoning about one's probabilistic
judgements. One can arrive at terribly wrong conclusions without being
incoherent in the sense meant by De Finetti.
Measured in terms of coherency, conventional probabilistic-reasoning apps
in 2007 already exceed the capabilities of humans by a tremendous margin.
So it seems to me that coherency should not therefore be seen as a major
limiting factor in AI, if not also AGI. Coherency is one of those things
about which we should be optimistic rather than pessimistic. What is a
machine intelligence if it is not a machine capable of coherent reasoning?
Achieving *accuracy* in our probabilistic judgements is a more difficult
problem, of course. Here there may be cause for pessimism.
-gts
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=303
