The trouble is: what is usually called "conjunction fallacy" can be
further divided into different cases. Some of them will usually be
avoid by an AGI (gts' example), some are hard to avoid, and some are
not really a fallacy at all (the classical "Linda the bank teller"
example) --- the traditional conclusions are all based on the implicit
assumption that "probability" is defined extensionally, so P(A&B) <
P(A). In situations where a measurement M is defined intensionally, it
is M(A&B) > M(A). The last case directly relates to the
"representative heuristic", which I discussed in
http://www.cogsci.indiana.edu/pub/wang.heuristic.ps

I'm not sure if Kolmogorov complexity plays a role in this or not.

Pei

On 2/8/07, Eliezer S. Yudkowsky <[EMAIL PROTECTED]> wrote:
Pei Wang wrote:
> On 2/8/07, gts <[EMAIL PROTECTED]> wrote:
>>
>> I gave an example of a Dutch book in a post to Russell in which an
>> incoherent thinker assigns a higher probability to intelligent life on
>> Mars than to mere life on Mars. Since the first hypothesis can be true
>> only if the second is true, it is incoherent to assign a higher
>> probability to the first than to the second.
>>
>> Coherence is basically just common sense applied to probabilistic
>> reasoning. I'm dismayed to learn from Ben that coherence is so difficult
>> to achieve in AGI.
>
> In simple cases like the above one, an AGI should achieve coherence
> with little difficulty. What an AGI cannot do is to guarantee
> coherence in all situations, which is impossible for human beings,
> neither --- think about situations where the incoherence of a bet
> setting needs many steps of inference, as well as necessary domain
> knowledge, to reveal.

Actually, conjunction fallacy is probably going to be one of the most
difficult of all biases to eliminate; it may even be provably impossible
for entities using any complexity-based variant of Occam's Razor, such
as Kolmogorov complexity.  If you ask for P(A) at time T and then P(A&B)
at time T+1, you should get a higher answer for P(A&B) wherever A is a
complex set of variable values that are insufficiently supported by
direct evidence, and B is a non-obvious compact explanation for A.
Thus, seeing B reduces the apparent Kolmogorov complexity of A, raising
A's prior.  You cannot always see B directly from A because this amounts
to always being able to find the most compact explanation, which amounts
to finding the shortest Turing machine that reproduces the data, which
is unsolvable by the halting problem.

I have sometimes thought that Levin search might yield provably
consistent probabilities - after all, a supposed explanation doesn't do
you any good if you can't derive data from it or prove that it halts.
Even so, seeing B directly from A might require an exponential search
too costly to perform.

Thus, conjunction fallacy - cases where being told about the hypothesis
B raises the subjective probability of P(A&B) over that you previously
gave to P(A) - is probably with us to stay, even unto the furthest
stars.  It may greatly diminish but not be utterly defeated.

--
Eliezer S. Yudkowsky                          http://singinst.org/
Research Fellow, Singularity Institute for Artificial Intelligence

-----
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


-----
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

Reply via email to