MENTAL.XGP[F76,JMC]5 - www.SailDart.org

perm filename MENTAL.XGP[F76,JMC]5 blob sn#255884 filedate 1977-01-03 generic text, type T, neo UTF8
/LMAR=0/XLINE=3/FONT#0=BAXL30/FONT#1=BAXM30/FONT#2=BASB30/FONT#3=SUB/FONT#4=SUP/FONT#5=BASL35/FONT#6=NGR25/FONT#7=MATH30/FONT#8=FIX25/FONT#9=GRKB30



␈↓ α∧␈↓␈↓ εddraft





















␈↓ α∧␈↓α␈↓ ∧↔ASCRIBING MENTAL QUALITIES TO MACHINES

␈↓ α∧␈↓Abstract:␈αAscribing␈αmental␈α
qualities␈αlike␈α␈↓↓beliefs,␈↓␈α
␈↓↓intentions␈↓␈αand␈α␈↓↓wants␈↓␈α
to␈αa␈αmachine␈α
is␈αsometimes
␈↓ α∧␈↓correct␈αif␈αdone␈αconservatively␈αand␈αis␈αsometimes␈α
necessary␈αto␈αexpress␈αwhat␈αis␈αknown␈αabout␈αits␈α
state.
␈↓ α∧␈↓We␈α⊗propose␈α⊗some␈α⊗new␈α⊗definitional␈α⊗tools␈α∃for␈α⊗this:␈α⊗second␈α⊗order␈α⊗structural␈α⊗definitions␈α∃and
␈↓ α∧␈↓definitions relative to an approximate theory.






␈↓ α∧␈↓(this draft of MENTAL[F76,JMC]@SU-AI compiled at 15:50 on January 3, 1977)














␈↓ α∧␈↓␈↓ ε|1␈↓ ∧



␈↓ α∧␈↓αINTRODUCTION

␈↓ α∧␈↓␈↓ αTTo␈αascribe␈αcertain␈α␈↓↓beliefs␈↓,␈α␈↓↓knowledge␈↓,␈α␈↓↓free␈αwill␈↓,␈α␈↓↓intentions␈↓,␈α␈↓↓consciousness␈↓,␈α␈↓↓abilities␈↓␈αor␈α␈↓↓wants␈↓␈αto
␈↓ α∧␈↓a␈α∩machine␈α∪or␈α∩computer␈α∩program␈α∪is␈α∩␈↓αlegitimate␈↓␈α∪when␈α∩such␈α∩an␈α∪ascription␈α∩expresses␈α∪the␈α∩same
␈↓ α∧␈↓information␈αabout␈αthe␈αmachine␈αthat␈αit␈αexpresses␈αabout␈αa␈αperson.␈α It␈αis␈α␈↓αuseful␈↓␈αwhen␈αthe␈αascription
␈↓ α∧␈↓helps␈αus␈αunderstand␈αthe␈αstructure␈αof␈αthe␈αmachine,␈αits␈αpast␈αor␈αfuture␈αbehavior,␈αor␈αhow␈αto␈αrepair␈αor
␈↓ α∧␈↓improve␈αit.␈α It␈αis␈αperhaps␈αnever␈α␈↓αlogically␈αrequired␈↓␈αeven␈αfor␈αhumans,␈αbut␈αexpressing␈αwhat␈αcan␈αbe
␈↓ α∧␈↓known␈α∂about␈α∞the␈α∂state␈α∂of␈α∞a␈α∂machine␈α∂in␈α∞a␈α∂particular␈α∞situation␈α∂in␈α∂an␈α∞utterance␈α∂or␈α∂expression␈α∞of
␈↓ α∧␈↓reasonable␈α∀length␈α∀may␈α∃require␈α∀ascribing␈α∀mental␈α∀qualities␈α∃or␈α∀qualities␈α∀isomorphic␈α∃to␈α∀them␈↓∧1␈↓.
␈↓ α∧␈↓Theories␈α
of␈α
belief,␈α
knowledge␈α
and␈α
wanting␈α
can␈α
be␈α
constructed␈α
for␈α
machines␈α
in␈α
a␈α∞simpler␈α
setting
␈↓ α∧␈↓than␈α↔for␈α↔humans␈α↔and␈α↔later␈α↔applied␈α⊗to␈α↔humans.␈α↔ Ascription␈α↔of␈α↔mental␈α↔qualities␈α↔is␈α⊗␈↓αmost
␈↓ α∧␈↓αstraightforward␈↓␈α∂for␈α∂machines␈α⊂of␈α∂known␈α∂structure␈α∂such␈α⊂as␈α∂thermostats␈α∂and␈α⊂computer␈α∂operating
␈↓ α∧␈↓systems, but is ␈↓αmost useful␈↓ when applied to entities whose structure is very incompletely known.

␈↓ α∧␈↓␈↓ αTThe␈α
above␈α
views␈α
are␈αmotivated␈α
by␈α
work␈α
in␈αartificial␈α
intelligence␈↓∧2␈↓␈α
(abbreviated␈α
AI).␈α They
␈↓ α∧␈↓can␈αbe␈αtaken␈αas␈αasserting␈αthat␈αmany␈αof␈αthe␈αphilosophical␈αproblems␈αof␈αmind␈αtake␈αa␈αpractical␈αform
␈↓ α∧␈↓as␈αsoon␈αas␈αone␈αtakes␈αseriously␈αthe␈α
idea␈αof␈αmaking␈αmachines␈αbehave␈αintelligently.␈α In␈αparticular,␈α
AI
␈↓ α∧␈↓raises␈α⊃for␈α⊃machines␈α⊃two␈α⊃issues␈α⊃that␈α⊃have␈α⊃heretofore␈α⊃been␈α⊃considered␈α⊃only␈α⊃in␈α⊃connection␈α⊃with
␈↓ α∧␈↓people.

␈↓ α∧␈↓␈↓ αTFirst,␈α∞in␈α∞designing␈α∞intelligent␈α∞programs␈α∞and␈α∞looking␈α∞at␈α∞them␈α∞from␈α∞the␈α∞outside␈α∞we␈α∞need␈α
to
␈↓ α∧␈↓determine␈α
the␈α
conditions␈α
under␈αwhich␈α
specific␈α
mental␈α
and␈αvolitional␈α
terms␈α
are␈α
applicable.␈α We␈α
can
␈↓ α∧␈↓exemplify␈α∂these␈α∂problems␈α⊂by␈α∂asking␈α∂when␈α∂might␈α⊂it␈α∂be␈α∂legitimate␈α∂to␈α⊂say␈α∂about␈α∂a␈α∂machine,␈α⊂␈↓↓"␈α∂It
␈↓ α∧␈↓↓knows I want a reservation to Boston, and it can give it to me, but it won't"␈↓.

␈↓ α∧␈↓␈↓ αTSecond,␈αwhen␈αwe␈αwant␈αa␈α␈↓αgenerally␈αintelligent␈↓␈↓∧3␈↓␈αcomputer␈αprogram,␈αwe␈αmust␈αbuild␈αinto␈αit␈αa
␈↓ α∧␈↓␈↓αgeneral␈αview␈↓␈αof␈αwhat␈αthe␈αworld␈αis␈αlike␈αwith␈αespecial␈αattention␈αto␈αfacts␈αabout␈αhow␈αthe␈αinformation
␈↓ α∧␈↓required␈αto␈αsolve␈αproblems␈αis␈αto␈αbe␈αobtained␈αand␈αused.␈α Thus␈αwe␈αmust␈αprovide␈αit␈αwith␈αsome␈αkind
␈↓ α∧␈↓of ␈↓↓metaphysics␈↓ (general world-view) and ␈↓↓epistemology␈↓ (theory of knowledge) however naive.

␈↓ α∧␈↓␈↓ αTAs␈αmuch␈αas␈αpossible,␈αwe␈αwill␈αascribe␈αmental␈αqualities␈αseparately␈αfrom␈αeach␈αother␈αinstead␈αof
␈↓ α∧␈↓bundling␈α∞them␈α∞in␈α∞a␈α∞concept␈α∞of␈α∂mind.␈α∞ This␈α∞is␈α∞necessary,␈α∞because␈α∞present␈α∞machines␈α∂have␈α∞rather
␈↓ α∧␈↓varied␈α∂little␈α∂minds;␈α∂the␈α∂mental␈α∂qualities␈α∂that␈α∂can␈α∂legitimately␈α∂be␈α∂ascribed␈α∂to␈α∂them␈α∂are␈α∂few␈α∞and
␈↓ α∧␈↓differ␈αfrom␈αmachine␈αto␈αmachine.␈α We␈αwill␈αnot␈α
even␈αtry␈αto␈αmeet␈αobjections␈αlike,␈α␈↓↓"Unless␈αit␈αalso␈α
does
␈↓ α∧␈↓↓X, it is illegitimate to speak of its having mental qualities."␈↓

␈↓ α∧␈↓␈↓ αTMachines␈αas␈αsimple␈αas␈αthermostats␈αcan␈αbe␈αsaid␈αto␈αhave␈αbeliefs,␈αand␈αhaving␈αbeliefs␈αseems␈αto
␈↓ α∧␈↓be␈α⊃a␈α⊃characteristic␈α⊃of␈α⊃most␈α⊃machines␈α⊃capable␈α⊃of␈α⊃problem␈α⊃solving␈α⊃performance.␈α⊃ However,␈α⊂the
␈↓ α∧␈↓machines␈α∩mankind␈α∩has␈α⊃so␈α∩far␈α∩found␈α∩it␈α⊃useful␈α∩to␈α∩construct␈α⊃rarely␈α∩have␈α∩beliefs␈α∩about␈α⊃beliefs.
␈↓ α∧␈↓(Beliefs␈αabout␈αbeliefs␈αwill␈αbe␈αneeded␈αby␈αcomputer␈αprograms␈αto␈αreason␈αabout␈αwhat␈αknowledge␈αthey
␈↓ α∧␈↓lack␈αand␈α
where␈αto␈α
get␈αit).␈α
 Mental␈αqualities␈α
peculiar␈αto␈α
human-like␈αmotivational␈α
structures,␈αsuch␈α
as
␈↓ α∧␈↓love␈α⊃and␈α⊂hate,␈α⊃will␈α⊂not␈α⊃be␈α⊃required␈α⊂for␈α⊃intelligent␈α⊂behavior,␈α⊃but␈α⊂we␈α⊃could␈α⊃probably␈α⊂program
␈↓ α∧␈↓computers␈α∩to␈α∩exhibit␈α∩them␈α∩if␈α∩we␈α∩wanted␈α⊃to,␈α∩because␈α∩our␈α∩common␈α∩sense␈α∩notions␈α∩about␈α⊃them
␈↓ α∧␈↓translate␈αreadily␈α
into␈αcertain␈αprogram␈α
and␈αdata␈α
structures.␈α Still␈αother␈α
mental␈αqualities,␈αe.g.␈α
 humor
␈↓ α∧␈↓and␈α⊃appreciation␈α⊃of␈α⊃beauty,␈α⊃seem␈α⊃much␈α⊃harder␈α⊃to␈α⊃model.␈α⊃ While␈α⊃we␈α⊃will␈α⊃be␈α⊃quite␈α∩liberal␈α⊃in
␈↓ α∧␈↓ascribing␈α
␈↓↓some␈↓␈αmental␈α
qualities␈αeven␈α
to␈αrather␈α
primitive␈αmachines,␈α
we␈αwill␈α
try␈αto␈α
be␈αconservative
␈↓ α∧␈↓in our criteria for ascribing any ␈↓↓particular␈↓ quality.


␈↓ α∧␈↓␈↓ ε|2␈↓ ∧



␈↓ α∧␈↓␈↓ αTThe␈α
successive␈α
sections␈α
of␈α
this␈α
paper␈α∞will␈α
give␈α
philosophical␈α
and␈α
AI␈α
reasons␈α∞for␈α
ascribing
␈↓ α∧␈↓beliefs␈αto␈αmachines,␈αtwo␈αnew␈αforms␈αof␈αdefinition␈αthat␈αseem␈αnecessary␈αfor␈αdefining␈αmental␈αqualities
␈↓ α∧␈↓and␈αexamples␈αof␈αtheir␈αuse,␈αexamples␈αof␈αsystems␈αto␈αwhich␈αmental␈αqualities␈αare␈αascribed,␈αsome␈αfirst
␈↓ α∧␈↓attempts␈α∩at␈α∩defining␈α⊃a␈α∩variety␈α∩of␈α∩mental␈α⊃qualities,␈α∩some␈α∩criticisms␈α⊃of␈α∩other␈α∩views␈α∩on␈α⊃mental
␈↓ α∧␈↓qualities, notes, and references.












































␈↓ α∧␈↓␈↓ ε|3␈↓ ∧



␈↓ α∧␈↓α␈↓ ∧nWHY ASCRIBE MENTAL QUALITIES?

␈↓ α∧␈↓␈↓ αT␈↓αWhy␈α
should␈α
we␈α
want␈α
to␈α
ascribe␈α
beliefs␈αto␈α
machines␈α
at␈α
all?␈↓␈α
This␈α
is␈α
the␈α
opposite␈αquestion␈α
to
␈↓ α∧␈↓that␈αof␈α␈↓↓reductionism␈↓.␈α Instead␈αof␈αasking␈αhow␈αmental␈αqualities␈αcan␈αbe␈α␈↓αreduced␈↓␈αto␈αphysical␈αones,␈αwe
␈↓ α∧␈↓ask␈α→how␈α_to␈α→␈↓αascribe␈↓␈α→mental␈α_qualities␈α→to␈α_physical␈α→systems.␈α→ This␈α_question␈α→may␈α→be␈α_more
␈↓ α∧␈↓straightforward and may lead to better answers to the questions of reductionism.

␈↓ α∧␈↓␈↓ αTTo␈α⊃put␈α⊃the␈α⊂issue␈α⊃sharply,␈α⊃consider␈α⊂a␈α⊃computer␈α⊃program␈α⊂for␈α⊃which␈α⊃we␈α⊃possess␈α⊂complete
␈↓ α∧␈↓listings.␈α
 The␈α
behavior␈α
of␈α
the␈α
program␈α
in␈α
any␈α
environment␈α
is␈α
determined␈α
from␈α
the␈α
structure␈α
of␈α
the
␈↓ α∧␈↓program␈α∂and␈α∞can␈α∂be␈α∂found␈α∞out␈α∂by␈α∞simulating␈α∂the␈α∂action␈α∞of␈α∂the␈α∞program␈α∂and␈α∂the␈α∞environment
␈↓ α∧␈↓without␈α∂having␈α∂to␈α∂deal␈α∂with␈α∂any␈α∂concept␈α∂of␈α∂belief.␈α∂ Nevertheless,␈α∂there␈α∂are␈α∂several␈α∂reasons␈α∞for
␈↓ α∧␈↓ascribing belief and other mental qualities:

␈↓ α∧␈↓␈↓ αT1.␈α
Although␈αwe␈α
may␈αknow␈α
the␈αprogram,␈α
its␈αstate␈α
at␈αa␈α
given␈αmoment␈α
is␈αusually␈α
not␈αdirectly
␈↓ α∧␈↓observable,␈αand␈αthe␈αfacts␈αwe␈αcan␈αobtain␈αabout␈αits␈αcurrent␈αstate␈αmay␈αbe␈αmore␈αreadily␈αexpressed␈αby
␈↓ α∧␈↓ascribing certain beliefs or wants than in any other way.

␈↓ α∧␈↓␈↓ αT2.␈α⊃Even␈α⊂if␈α⊃we␈α⊃can␈α⊂simulate␈α⊃the␈α⊃interaction␈α⊂of␈α⊃our␈α⊃program␈α⊂with␈α⊃its␈α⊃environment␈α⊂using
␈↓ α∧␈↓another␈α
more␈α
comprehensive␈α∞program,␈α
the␈α
simulation␈α∞may␈α
be␈α
a␈α
billion␈α∞times␈α
too␈α
slow.␈α∞ We␈α
also
␈↓ α∧␈↓may␈αnot␈αhave␈αthe␈αinitial␈αconditions␈αof␈αthe␈αenvironment␈αor␈αthe␈αenvironment's␈αlaws␈αof␈αmotion␈αin␈αa
␈↓ α∧␈↓suitable␈α∂form,␈α∞whereas␈α∂it␈α∞may␈α∂be␈α∞feasible␈α∂to␈α∞make␈α∂a␈α∞prediction␈α∂of␈α∞the␈α∂effects␈α∞of␈α∂the␈α∂beliefs␈α∞we
␈↓ α∧␈↓ascribe to the program without any computer at all.

␈↓ α∧␈↓␈↓ αT3.␈α∂Ascribing␈α∂beliefs␈α∞may␈α∂allow␈α∂deriving␈α∂general␈α∞statements␈α∂about␈α∂the␈α∂program's␈α∞behavior
␈↓ α∧␈↓that could not be obtained from any finite number of simulations.

␈↓ α∧␈↓␈↓ αT4.␈α
 The␈α
belief␈α
and␈α
goal␈α
structures␈α
we␈α∞ascribe␈α
to␈α
the␈α
program␈α
may␈α
be␈α
easier␈α∞to␈α
understand
␈↓ α∧␈↓than the details of program as expressed in its listing.

␈↓ α∧␈↓␈↓ αT5.␈α∂The␈α∂belief␈α∞and␈α∂goal␈α∂structure␈α∞is␈α∂likely␈α∂to␈α∂be␈α∞close␈α∂to␈α∂the␈α∞structure␈α∂the␈α∂designer␈α∂of␈α∞the
␈↓ α∧␈↓program␈αhad␈αin␈αmind,␈αand␈αit␈αmay␈αbe␈αeasier␈αto␈αdebug␈αthe␈αprogram␈αin␈αterms␈αof␈αthis␈αstructure␈αthan
␈↓ α∧␈↓directly␈αfrom␈αthe␈αlisting.␈α
 In␈αfact,␈αit␈αis␈αoften␈α
possible␈αfor␈αsomeone␈αto␈α
correct␈αa␈αfault␈αby␈αreasoning␈α
in
␈↓ α∧␈↓general␈α∞terms␈α∂about␈α∞the␈α∂information␈α∞in␈α∞a␈α∂program␈α∞or␈α∂machine,␈α∞diagnosing␈α∞what␈α∂is␈α∞wrong␈α∂as␈α∞a
␈↓ α∧␈↓false␈α
belief,␈α
and␈α
looking␈α∞at␈α
the␈α
details␈α
of␈α
the␈α∞program␈α
or␈α
machine␈α
only␈α
sufficiently␈α∞to␈α
determine
␈↓ α∧␈↓how the false belief is represented and what mechanism caused it to arise.␈↓∧4␈↓

␈↓ α∧␈↓␈↓ αTAll␈α
the␈α
above␈α
reasons␈α
for␈α
ascribing␈α
beliefs␈α
are␈α
epistemological;␈α
i.e.␈α
ascribing␈α
beliefs␈α
is␈α
needed
␈↓ α∧␈↓to␈α∞adapt␈α∞to␈α∂limitations␈α∞on␈α∞our␈α∞ability␈α∂to␈α∞acquire␈α∞knowledge,␈α∞use␈α∂it␈α∞for␈α∞prediction,␈α∂and␈α∞establish
␈↓ α∧␈↓generalizations␈α
in␈α
terms␈α
of␈α
the␈α
elementary␈α
structure␈αof␈α
the␈α
program.␈α
 Perhaps␈α
this␈α
is␈α
the␈αgeneral
␈↓ α∧␈↓reason for ascribing higher levels of organization to systems.

␈↓ α∧␈↓␈↓ αTComputers␈αgive␈αrise␈αto␈αnumerous␈αexamples␈αof␈αbuilding␈αa␈αhigher␈αstructure␈αon␈αthe␈αbasis␈αof␈αa
␈↓ α∧␈↓lower␈α
and␈α
conducting␈α
subsequent␈α
analyses␈α
using␈α
the␈α
higher␈α
structure.␈α
 The␈α
geometry␈α
of␈αthe␈α
electric
␈↓ α∧␈↓fields␈α
in␈αa␈α
transistor␈α
and␈αits␈α
chemical␈α
composition␈αgive␈α
rise␈αto␈α
its␈α
properties␈αas␈α
an␈α
electric␈αcircuit
␈↓ α∧␈↓element.␈α
 Transistors␈α
are␈αcombined␈α
in␈α
small␈αcircuits␈α
and␈α
powered␈α
in␈αstandard␈α
ways␈α
to␈αmake␈α
logical
␈↓ α∧␈↓elements␈α
such␈α
as␈α
ANDs,␈α
ORs,␈α
NOTs␈α
and␈α
flip-flops.␈α
 Computers␈α
are␈α
designed␈α
with␈α∞these␈α
logical
␈↓ α∧␈↓elements␈αto␈αobey␈αa␈αdesired␈αorder␈αcode;␈αthe␈αdesigner␈αusually␈αneedn't␈αconsider␈αthe␈αproperties␈α
of␈αthe


␈↓ α∧␈↓␈↓ ε|4␈↓ ∧



␈↓ α∧␈↓transistors␈αas␈αcircuit␈α
elements.␈α The␈αdesigner␈α
of␈αa␈αhigher␈α
level␈αlanguage␈αworks␈α
with␈αthe␈αorder␈α
code
␈↓ α∧␈↓and␈α⊂doesn't␈α∂have␈α⊂to␈α⊂know␈α∂about␈α⊂the␈α⊂ANDs␈α∂and␈α⊂ORs;␈α∂the␈α⊂user␈α⊂of␈α∂the␈α⊂higher␈α⊂order␈α∂language
␈↓ α∧␈↓needn't know the computer's order code.

␈↓ α∧␈↓␈↓ αTIn␈αthe␈αabove␈αcases,␈α
users␈αof␈αthe␈αhigher␈αlevel␈α
can␈αcompletely␈αignore␈αthe␈αlower␈α
level,␈αbecause
␈↓ α∧␈↓the␈αbehavior␈αof␈αthe␈αhigher␈α
level␈αsystem␈αis␈αcompletely␈αdetermined␈α
by␈αthe␈αvalues␈αof␈αthe␈αhigher␈α
level
␈↓ α∧␈↓variables;␈α
e.g.␈α in␈α
order␈αto␈α
determine␈αthe␈α
outcome␈αof␈α
a␈αcomputer␈α
program,␈αone␈α
needn't␈αconsider␈α
the
␈↓ α∧␈↓flip-flops.␈α
 However,␈α
when␈α
we␈α
ascribe␈α
mental␈α
structure␈α
to␈α
humans␈α
or␈α
goals␈α
to␈α
society,␈α∞we␈α
always
␈↓ α∧␈↓get␈α∞highly␈α∞incomplete␈α∂systems;␈α∞the␈α∞higher␈α∂level␈α∞behavior␈α∞cannot␈α∂be␈α∞fully␈α∞predicted␈α∂from␈α∞higher
␈↓ α∧␈↓level␈α⊃observations␈α⊃and␈α⊃higher␈α⊂level␈α⊃"laws"␈α⊃even␈α⊃when␈α⊂the␈α⊃underlying␈α⊃lower␈α⊃level␈α⊃behavior␈α⊂is
␈↓ α∧␈↓determinate.

␈↓ α∧␈↓␈↓ αTIn␈α
order␈α
to␈α
program␈α
a␈α
computer␈α
to␈α
obtain␈α
information␈α
and␈α
co-operation␈α
from␈α∞people␈α
and
␈↓ α∧␈↓other␈α
machines,␈α
we␈α
will␈α
have␈α
to␈α
make␈α
it␈α
ascribe␈α
knowledge,␈α
belief,␈α
and␈α
wants␈α
to␈α∞other␈α
machines
␈↓ α∧␈↓and␈α∞people.␈α∂ For␈α∞example,␈α∂a␈α∞program␈α∂that␈α∞plans␈α∂trips␈α∞will␈α∂have␈α∞to␈α∂ascribe␈α∞knowledge␈α∂to␈α∞travel
␈↓ α∧␈↓agents␈α⊂and␈α⊂to␈α⊂the␈α⊂airline␈α⊂reservation␈α⊂computers.␈α⊂ It␈α⊂will␈α⊂even␈α⊂have␈α⊂to␈α⊂treat␈α⊂the␈α⊂notion␈α⊂of␈α⊂the
␈↓ α∧␈↓presence␈αof␈αinformation␈αin␈αbooks,␈αpresumably␈αby␈αascribing␈αa␈αweak␈αform␈αof␈αknowledge.␈α The␈αmore
␈↓ α∧␈↓powerful␈α⊂the␈α⊂program␈α⊃in␈α⊂interpreting␈α⊂what␈α⊃it␈α⊂is␈α⊂told,␈α⊂the␈α⊃less␈α⊂it␈α⊂has␈α⊃to␈α⊂know␈α⊂about␈α⊃how␈α⊂the
␈↓ α∧␈↓information␈α
it␈αcan␈α
receive␈α
is␈αrepresented␈α
internally␈α
and␈αpresented␈α
to␈α
it␈αand␈α
the␈α
more␈αits␈α
ascriptions
␈↓ α∧␈↓of knowledge will look like human ascriptions of knowledge to each other.





























␈↓ α∧␈↓␈↓ ε|5␈↓ ∧



␈↓ α∧␈↓αTWO␈α METHODS␈α OF␈α DEFINITION␈α AND␈α THEIR␈α APPLICATION␈α TO␈α∨MENTAL
␈↓ α∧␈↓αQUALITIES

␈↓ α∧␈↓␈↓ αTIn␈α∂our␈α⊂opinion,␈α∂a␈α∂major␈α⊂source␈α∂of␈α⊂problems␈α∂in␈α∂defining␈α⊂mental␈α∂and␈α⊂other␈α∂philosophical
␈↓ α∧␈↓concepts␈α
is␈α
the␈α
weakness␈αof␈α
the␈α
methods␈α
of␈α
definition␈αthat␈α
have␈α
been␈α
␈↓↓explicitly␈↓␈α
used.␈α Therefore
␈↓ α∧␈↓we␈α
introduce␈α
two␈α
new␈↓∧5␈↓␈α
kinds␈α
of␈α
definition:␈α
␈↓↓second␈α
order␈α
structural␈α
definition␈↓␈α
and␈α␈↓↓definition␈α
relative
␈↓ α∧␈↓↓to an approximate theory␈↓ and their application to defining mental qualities.

␈↓ α∧␈↓1. ␈↓αSecond Order Structural Definition.␈↓

␈↓ α∧␈↓␈↓ αTStructural␈α∩definitions␈α∩of␈α∩qualities␈α∩are␈α∩given␈α∩in␈α∩terms␈α∩of␈α∩the␈α∩state␈α∩of␈α∩the␈α∪system␈α∩being
␈↓ α∧␈↓described while behavioral definitions are given in terms of its actual or potential behavior␈↓∧6␈↓.

␈↓ α∧␈↓␈↓ αTIf␈α∂the␈α∂structure␈α⊂of␈α∂the␈α∂machine␈α∂is␈α⊂known,␈α∂one␈α∂can␈α∂give␈α⊂an␈α∂ad␈α∂hoc␈α∂␈↓↓first␈α⊂order␈α∂structural
␈↓ α∧␈↓↓definition␈↓.␈α
 This␈α
is␈α
a␈α
predicate␈α
␈↓↓B(s,p)␈↓␈α
where␈α
␈↓↓s␈↓␈α
represents␈α
a␈α
state␈α
of␈α
the␈α
machine␈α
and␈α
␈↓↓p␈↓␈α
represents␈α
a
␈↓ α∧␈↓sentence␈αin␈α
a␈αsuitable␈α
language,␈αand␈α
␈↓↓B(s,p)␈↓␈αis␈αthe␈α
assertion␈αthat␈α
when␈αthe␈α
machine␈αis␈α
in␈αstate␈α␈↓↓s,␈↓␈α
it
␈↓ α∧␈↓␈↓↓believes␈↓␈α⊂the␈α⊂sentence␈α⊂␈↓↓p.␈↓␈α⊂(The␈α⊂considerations␈α⊃of␈α⊂this␈α⊂paper␈α⊂are␈α⊂neutral␈α⊂in␈α⊂deciding␈α⊃whether␈α⊂to
␈↓ α∧␈↓regard␈α
the␈α
object␈α
of␈α∞belief␈α
as␈α
a␈α
sentence␈α∞or␈α
to␈α
use␈α
a␈α
modal␈α∞operator␈α
or␈α
to␈α
admit␈α∞␈↓↓propositions␈↓␈α
as
␈↓ α∧␈↓abstract␈αobjects␈αthat␈αcan␈αbe␈αbelieved.␈α The␈αpaper␈αis␈αwritten␈αas␈αthough␈αsentences␈αare␈αthe␈αobjects␈αof
␈↓ α∧␈↓belief,␈αbut␈αin␈α(McCarthy␈α1976)␈αI␈αfavor␈α
propositions).␈α A␈αgeneral␈α␈↓↓first␈↓␈α␈↓↓order␈↓␈αstructural␈αdefinition␈α
of
␈↓ α∧␈↓belief␈αwould␈α
be␈αa␈α
predicate␈α␈↓↓B(W,M,s,p)␈↓␈α
where␈α␈↓↓W␈↓␈α
is␈αthe␈α
"world"␈αin␈α
which␈αthe␈α
machine␈α␈↓↓M␈↓␈α
whose
␈↓ α∧␈↓beliefs␈α
are␈α
in␈α
question␈αis␈α
situated.␈α
 I␈α
do␈α
not␈αsee␈α
how␈α
to␈α
give␈α
such␈αa␈α
definition␈α
of␈α
belief,␈α
and␈αI␈α
think
␈↓ α∧␈↓it is impossible.  Therefore we turn to second order definitions.

␈↓ α∧␈↓␈↓ αTA␈α∩second␈α⊃order␈α∩structural␈α⊃definition␈α∩of␈α⊃belief␈α∩is␈α⊃a␈α∩second␈α⊃order␈α∩predicate␈α⊃␈↓↓β(W,M,B).␈↓
␈↓ α∧␈↓␈↓↓β(W,M,B)␈↓␈αasserts␈αthat␈αthe␈αfirst␈αorder␈αpredicate␈α␈↓↓B␈↓␈αis␈αa␈α"good"␈αnotion␈αof␈αbelief␈αfor␈αthe␈αmachine␈α␈↓↓M␈↓
␈↓ α∧␈↓in␈αthe␈αworld␈α␈↓↓W.␈↓␈αHere␈α"good"␈αmeans␈αthat␈αthe␈αbeliefs␈αthat␈α␈↓↓B␈↓␈αascribes␈αto␈α␈↓↓M␈↓␈αagree␈αwith␈αour␈αideas␈αof
␈↓ α∧␈↓what␈α⊂beliefs␈α∂␈↓↓M␈↓␈α⊂would␈α∂have,␈α⊂not␈α⊂that␈α∂the␈α⊂beliefs␈α∂themselves␈α⊂are␈α∂true.␈α⊂ The␈α⊂axiomatizations␈α∂of
␈↓ α∧␈↓belief in the literature are partial second order definitions.

␈↓ α∧␈↓␈↓ αTIn␈α⊂general,␈α⊂␈↓αa␈α⊃second␈α⊂order␈α⊂definition␈α⊃gives␈α⊂criteria␈α⊂for␈α⊃criticizing␈α⊂an␈α⊂ascription␈α⊃of␈α⊂a
␈↓ α∧␈↓αquality␈αto␈αa␈αsystem.␈↓␈αWe␈α
suggest␈αthat␈αboth␈αour␈αcommon␈α
sense␈αand␈αscientific␈αusage␈αof␈α
not-directly-
␈↓ α∧␈↓observable␈α
qualities␈αcorresponds␈α
more␈α
losely␈αto␈α
second␈αorder␈α
structural␈α
definition␈αthan␈α
to␈αany␈α
kind
␈↓ α∧␈↓of␈α∞behavioral␈α∞definition.␈α∞ Note␈α∞that␈α∞a␈α
second␈α∞order␈α∞definition␈α∞cannot␈α∞guarantee␈α∞that␈α∞there␈α
exist
␈↓ α∧␈↓predicates␈α␈↓↓B␈↓␈αmeeting␈αthe␈αcriterion␈α
β␈αor␈αthat␈αsuch␈αa␈α␈↓↓B␈↓␈α
is␈αunique.␈α Some␈αqualities␈αare␈α
best␈αdefined
␈↓ α∧␈↓jointly with related qualities, e.g. beliefs and goals may require joint treatment.

␈↓ α∧␈↓␈↓ αTSecond␈αorder␈αdefinitions␈αcriticize␈αwhole␈αbelief␈αstructures␈αrather␈αthan␈αindividual␈αbeliefs.␈α We
␈↓ α∧␈↓can␈αtreat␈αindividual␈αbeliefs␈αby␈αsaying␈αthat␈αa␈αsystem␈αbelieves␈α␈↓↓p␈↓␈αin␈αstate␈α␈↓↓s␈↓␈αprovided␈αall␈α"reasonably
␈↓ α∧␈↓good" ␈↓↓B␈↓'s satisfy ␈↓↓B(s,p)␈↓.  Thus we are distinguishing the "intersection" of the reasonably good ␈↓↓B␈↓'s.

␈↓ α∧␈↓␈↓ αT(An␈α∀analogy␈α∀with␈α∀cryptography␈α∀may␈α∀be␈α∪helpful.␈α∀ We␈α∀solve␈α∀a␈α∀cryptogram␈α∀by␈α∪making
␈↓ α∧␈↓hypotheses␈αabout␈αthe␈αstructure␈αof␈αthe␈αcipher␈αand␈αabout␈αthe␈αtranslation␈αof␈αparts␈αof␈αthe␈αcipher␈αtext.
␈↓ α∧␈↓Our␈α
solution␈α
is␈α
complete␈α
when␈α
we␈α
have␈α"guessed"␈α
a␈α
cipher␈α
system␈α
that␈α
produces␈α
the␈αcryptogram
␈↓ α∧␈↓from␈α∂a␈α∂plausible␈α∂plaintext␈α⊂message.␈α∂ Though␈α∂we␈α∂never␈α∂prove␈α⊂that␈α∂our␈α∂solution␈α∂is␈α⊂unique,␈α∂two
␈↓ α∧␈↓different␈αsolutions␈αare␈αalmost␈αnever␈αfound␈αexcept␈αfor␈αvery␈αshort␈αcryptograms.␈α In␈αthe␈αanalogy,␈αthe
␈↓ α∧␈↓second␈αorder␈αdefinition␈α
β␈αcorresponds␈αto␈α
the␈αgeneral␈αidea␈α
of␈αencipherment,␈αand␈α
␈↓↓B␈↓␈αis␈αthe␈α
particular


␈↓ α∧␈↓␈↓ ε|6␈↓ ∧



␈↓ α∧␈↓system␈α
used.␈α∞ While␈α
we␈α∞will␈α
rarely␈α∞be␈α
able␈α∞to␈α
prove␈α∞uniqueness,␈α
we␈α∞don't␈α
expect␈α∞to␈α
find␈α∞two␈α
␈↓↓B␈↓s
␈↓ α∧␈↓both satisfying β).

␈↓ α∧␈↓␈↓ αTIt␈αseems␈αto␈αme␈αthat␈αthere␈αshould␈αbe␈αa␈αmetatheorem␈αof␈αmathematical␈αlogic␈αasserting␈αthat␈αnot
␈↓ α∧␈↓all␈α∪second␈α∪order␈α∪definitions␈α∪can␈α∪be␈α∩reduced␈α∪to␈α∪first␈α∪order␈α∪definitions␈α∪and␈α∪further␈α∩theorems
␈↓ α∧␈↓characterizing␈αthose␈α
second␈αorder␈α
definitions␈αthat␈αadmit␈α
such␈αreductions.␈α
 Such␈αtechnical␈αresults,␈α
if
␈↓ α∧␈↓they␈α⊂can␈α∂be␈α⊂found,␈α∂may␈α⊂be␈α∂helpful␈α⊂in␈α∂philosophy␈α⊂and␈α∂in␈α⊂the␈α∂construction␈α⊂of␈α⊂formal␈α∂scientific
␈↓ α∧␈↓theories.␈α⊃ I␈α⊃would␈α⊃conjecture␈α⊃that␈α⊃many␈α⊃of␈α⊃the␈α⊃informal␈α⊃philosophical␈α⊃arguments␈α⊃that␈α⊂certain
␈↓ α∧␈↓mental␈αconcepts␈αcannot␈αbe␈αreduced␈αto␈αphysics␈αwill␈αturn␈αout␈αto␈αbe␈αsketches␈αof␈αarguments␈αthat␈αthese
␈↓ α∧␈↓concepts require second (or higher) order definitions.

␈↓ α∧␈↓␈↓ αTHere␈αis␈αan␈αapproximate␈α
second␈αorder␈αdefinition␈αof␈αbelief.␈α
 For␈αeach␈αstate␈α␈↓↓s␈↓␈αof␈α
the␈αmachine
␈↓ α∧␈↓and␈α⊂each␈α⊂sentence␈α⊂␈↓↓p␈↓␈α⊂in␈α⊂a␈α⊂suitable␈α⊂language␈α⊂␈↓↓L,␈↓␈α⊂we␈α⊂assign␈α⊂truth␈α⊂to␈α⊂␈↓↓B(s,p)␈↓␈α⊂if␈α⊂and␈α⊂only␈α⊃if␈α⊂the
␈↓ α∧␈↓machine␈α⊂is␈α⊂considered␈α⊂to␈α⊂believe␈α⊂␈↓↓p␈↓␈α⊂when␈α⊂it␈α⊂is␈α⊂in␈α⊂state␈α⊂␈↓↓s␈↓.␈α⊂ The␈α⊂language␈α⊂␈↓↓L␈↓␈α⊂is␈α⊂chosen␈α⊃for␈α⊂our
␈↓ α∧␈↓convenience,␈α
and␈αthere␈α
is␈α
no␈αassumption␈α
that␈α
the␈αmachine␈α
explicitly␈α
represents␈αsentences␈α
of␈α
␈↓↓L␈↓␈αin
␈↓ α∧␈↓any␈α∂way.␈α∂ Thus␈α∂we␈α⊂can␈α∂talk␈α∂about␈α∂the␈α∂beliefs␈α⊂of␈α∂Chinese,␈α∂dogs,␈α∂corporations,␈α⊂thermostats,␈α∂and
␈↓ α∧␈↓computer␈α∂operating␈α∂systems␈α∂without␈α∞assuming␈α∂that␈α∂they␈α∂use␈α∞English␈α∂or␈α∂our␈α∂favorite␈α∂first␈α∞order
␈↓ α∧␈↓language.␈α∞ ␈↓↓L␈↓␈α∞may␈α∞or␈α∞may␈α∂not␈α∞be␈α∞the␈α∞language␈α∞be␈α∞the␈α∂language␈α∞we␈α∞are␈α∞using␈α∞for␈α∂making␈α∞other
␈↓ α∧␈↓assertions,␈α
e.g.␈α
we␈αcould,␈α
writing␈α
in␈αEnglish,␈α
systematically␈α
use␈α
French␈αsentences␈α
as␈α
objects␈αof␈α
belief.
␈↓ α∧␈↓However,␈αthe␈αbest␈αchoice␈αfor␈αartificial␈αintelligence␈αwork␈αmay␈αbe␈αto␈αmake␈α␈↓↓L␈↓␈αa␈αsubset␈αof␈αour␈α"outer"
␈↓ α∧␈↓language restricted so as to avoid the paradoxical self-references of (Montague 1963).

␈↓ α∧␈↓␈↓ αTWe␈α⊃now␈α⊃subject␈α⊃␈↓↓B(s,p)␈↓␈α⊃to␈α⊃certain␈α⊃criteria;␈α⊃i.e.␈α⊃β␈↓↓(B,W)␈↓␈α⊃is␈α⊃considered␈α⊃true␈α⊃provided␈α⊃the
␈↓ α∧␈↓following conditions are satisfied:

␈↓ α∧␈↓␈↓ β$1.1.␈αThe␈αset␈α␈↓↓Bel(s)␈↓␈αof␈αbeliefs,␈αi.e.␈αthe␈αset␈αof␈α␈↓↓p␈↓'s␈αfor␈αwhich␈α␈↓↓B(s,p)␈↓␈αis␈αassigned␈αtrue␈αwhen
␈↓ α∧␈↓␈↓↓M␈↓ is in state ␈↓↓s␈↓ contains sufficiently "obvious" consequences of some of its members.

␈↓ α∧␈↓␈↓ β$1.2.␈α ␈↓↓Bel(s)␈↓␈αchanges␈αin␈αa␈αreasonable␈αway␈αwhen␈αthe␈αstate␈αchanges␈αin␈αtime.␈α We␈αlike␈α
new
␈↓ α∧␈↓beliefs␈α∞to␈α∞be␈α
logical␈α∞or␈α∞"plausible"␈α
consequences␈α∞of␈α∞old␈α
ones␈α∞or␈α∞to␈α
come␈α∞in␈α∞as␈α∞␈↓↓communications␈↓␈α
in
␈↓ α∧␈↓some␈α∂language␈α∂on␈α∂the␈α∂input␈α∂lines␈α∂or␈α∂to␈α∂be␈α∂␈↓↓observations␈↓,␈α∂i.e.␈α∂ beliefs␈α∂about␈α∂the␈α∂environment␈α∂the
␈↓ α∧␈↓information␈α∂for␈α∂which␈α⊂comes␈α∂in␈α∂on␈α∂the␈α⊂input␈α∂lines.␈α∂ The␈α∂set␈α⊂of␈α∂beliefs␈α∂should␈α∂not␈α⊂change␈α∂too
␈↓ α∧␈↓rapidly as the state changes with time.

␈↓ α∧␈↓␈↓ β$1.3.␈α∀ We␈α∀prefer␈α∀the␈α∀set␈α∀of␈α∀beliefs␈α∀to␈α∀be␈α∀as␈α∀consistent␈α∀as␈α∀possible.␈α∀ (Admittedly,
␈↓ α∧␈↓consistency␈α
is␈α∞not␈α
a␈α∞quantitative␈α
concept␈α∞in␈α
mathematical␈α∞logic␈α
-␈α∞a␈α
system␈α∞is␈α
either␈α∞consistent␈α
or
␈↓ α∧␈↓not,␈α⊃but␈α⊃it␈α⊃would␈α⊃seem␈α⊃that␈α⊃we␈α⊃will␈α⊃sometimes␈α⊃have␈α⊃to␈α⊃ascribe␈α⊃inconsistent␈α⊃sets␈α⊃of␈α⊃beliefs␈α⊃to
␈↓ α∧␈↓machines␈αand␈αpeople.␈α Our␈αintuition␈αsays␈αthat␈αwe␈αshould␈αbe␈αable␈αto␈αmaintain␈αareas␈αof␈αconsistency
␈↓ α∧␈↓in␈α∞our␈α∞beliefs␈α∞and␈α∞that␈α
it␈α∞may␈α∞be␈α∞especially␈α∞important␈α
to␈α∞avoid␈α∞inconsistencies␈α∞in␈α∞the␈α
machine's
␈↓ α∧␈↓purely analytic beliefs).

␈↓ α∧␈↓␈↓ β$1.4.␈α∞ Our␈α∞criteria␈α∂for␈α∞belief␈α∞systems␈α∂can␈α∞be␈α∞strengthened␈α∞if␈α∂we␈α∞identify␈α∞some␈α∂of␈α∞the
␈↓ α∧␈↓machine's␈α
beliefs␈αas␈α
expressing␈αgoals,␈α
i.e.␈αif␈α
we␈αhave␈α
beliefs␈αof␈α
the␈αform␈α
"It␈αwould␈α
be␈αgood␈α
if␈α...".
␈↓ α∧␈↓Then␈α
we␈α
can␈α
ask␈α
that␈α
the␈α
machine's␈α
behavior␈α
be␈α
somewhat␈α
␈↓↓rational␈↓,␈α
i.e.␈α
 ␈↓↓it␈α
does␈α
what␈α∞it␈α
believes
␈↓ α∧␈↓↓will␈αachieve␈αits␈αgoals␈↓.␈αThe␈αmore␈αof␈αits␈αbehavior␈αwe␈αcan␈αaccount␈αfor␈αin␈αthis␈αway,␈αthe␈αbetter␈αwe␈αwill
␈↓ α∧␈↓like␈αthe␈αfunction␈α␈↓↓B(s,p)␈↓.␈α We␈αalso␈αwould␈αlike␈αto␈αregard␈αinternal␈αstate␈αchanges␈αas␈αchanges␈αin␈αbelief
␈↓ α∧␈↓in so far as this is reasonable.


␈↓ α∧␈↓␈↓ ε|7␈↓ ∧



␈↓ α∧␈↓␈↓ β$1.5.␈α
 If␈α
the␈α
machine␈α
communicates,␈α
i.e.␈α
emits␈α
sentences␈α
in␈α
some␈α
language␈α
that␈α
can␈α
be
␈↓ α∧␈↓interpreted␈α∞as␈α∂assertions,␈α∞questions␈α∞and␈α∂commands,␈α∞we␈α∞will␈α∂want␈α∞the␈α∞assertions␈α∂to␈α∞be␈α∂among␈α∞its
␈↓ α∧␈↓beliefs␈α⊂unless␈α⊃we␈α⊂are␈α⊃ascribing␈α⊂to␈α⊂it␈α⊃a␈α⊂goal␈α⊃or␈α⊂subgoal␈α⊂that␈α⊃involves␈α⊂lying.␈α⊃ We␈α⊂will␈α⊃be␈α⊂most
␈↓ α∧␈↓satisfied␈α∂with␈α∞our␈α∂belief␈α∞ascription,␈α∂if␈α∂we␈α∞can␈α∂account␈α∞for␈α∂its␈α∞communications␈α∂as␈α∂furthering␈α∞the
␈↓ α∧␈↓goals we are ascribing.

␈↓ α∧␈↓␈↓ β$1.6.␈α Sometimes␈αwe␈αshall␈αwant␈αto␈αascribe␈αintrospective␈αbeliefs,␈αe.g.␈αa␈αbelief␈αthat␈αit␈αdoes
␈↓ α∧␈↓not know how to fly to Boston or even that it doesn't know what it wants in a certain situation.

␈↓ α∧␈↓␈↓ β$1.7.␈α
Finally,␈α∞we␈α
will␈α
prefer␈α∞a␈α
more␈α
economical␈α∞ascription␈α
␈↓↓B␈↓␈α
to␈α∞a␈α
less␈α∞economical␈α
one.
␈↓ α∧␈↓The␈α
fewer␈α
beliefs␈αwe␈α
ascribe␈α
and␈αthe␈α
less␈α
they␈αchange␈α
with␈α
state␈αconsistent␈α
with␈α
accounting␈αfor␈α
the
␈↓ α∧␈↓behavior and the internal state changes, the better we will like it.

␈↓ α∧␈↓␈↓ αTThe␈α
above␈α
criteria␈α
have␈α
been␈α
formulated␈α
somewhat␈α
vaguely.␈α
 This␈α
would␈α
be␈α
bad␈α∞if␈α
there
␈↓ α∧␈↓were␈αwidely␈α
different␈αascriptions␈α
of␈αbeliefs␈α
to␈αa␈αparticular␈α
machine␈αthat␈α
all␈αmet␈α
our␈αcriteria␈α
or␈αif
␈↓ α∧␈↓the␈α∞criteria␈α∞allowed␈α∞ascriptions␈α∞that␈α∞differed␈α∞widely␈α∞from␈α∞our␈α∞intuitions.␈α∞ My␈α∞present␈α∞opinion␈α
is
␈↓ α∧␈↓that␈α∞more␈α∞thought␈α
will␈α∞make␈α∞the␈α
criteria␈α∞somewhat␈α∞more␈α
precise␈α∞at␈α∞no␈α
cost␈α∞in␈α∞applicability,␈α
but
␈↓ α∧␈↓that␈αthey␈α␈↓↓should␈↓␈αstill␈αremain␈αrather␈αvague,␈αi.e.␈αwe␈αshall␈αwant␈αto␈αascribe␈αbelief␈αin␈αa␈α␈↓↓family␈↓␈αof␈αcases.
␈↓ α∧␈↓However,␈α⊃even␈α⊃at␈α⊃the␈α⊃present␈α⊃level␈α⊃of␈α⊃vagueness,␈α⊃there␈α⊃probably␈α⊃won't␈α⊃be␈α∩radically␈α⊃different
␈↓ α∧␈↓equally␈α
"good"␈αascriptions␈α
of␈αbelief␈α
for␈α
systems␈αof␈α
practical␈αinterest.␈α
 If␈α
there␈αwere,␈α
we␈αwould␈α
notice
␈↓ α∧␈↓unresolvable ambiguities in our ascriptions of belief to our acquaintances.

␈↓ α∧␈↓␈↓ αTWhile␈αwe␈αmay␈α
not␈αwant␈αto␈α
pin␈αdown␈αour␈α
general␈αidea␈αof␈α
belief␈αto␈αa␈α
single␈αaxiomatization,
␈↓ α∧␈↓we␈α
will␈αneed␈α
to␈αbuild␈α
precise␈α
axiomatizations␈αof␈α
belief␈αand␈α
other␈αmental␈α
qualities␈α
into␈αparticular
␈↓ α∧␈↓intelligent computer programs.

␈↓ α∧␈↓2. ␈↓αDefinitions relative to an approximate theory␈↓.

␈↓ α∧␈↓␈↓ αTOur␈αapproach␈αto␈αascribing␈α␈↓↓intentions␈↓␈αand␈α␈↓↓free␈αwill␈↓␈αand␈αto␈αdistinguishing␈αa␈α␈↓↓deliberate␈αaction␈↓
␈↓ α∧␈↓from␈α
an␈α∞occurrence␈α
requires␈α
yet␈α∞another␈α
means␈α∞of␈α
definition.␈α
 We␈α∞will␈α
want␈α
to␈α∞call␈α
an␈α∞output␈α
a
␈↓ α∧␈↓␈↓↓deliberate␈α∂action␈↓␈α∂if␈α∂the␈α∂output␈α∂would␈α∂have␈α∂been␈α∂different␈α∂if␈α∂the␈α∂machine's␈α∂intentions␈α∂had␈α∞been
␈↓ α∧␈↓different.␈α This␈αrequires␈αa␈αcriterion␈αfor␈α
the␈αtruth␈αof␈αthe␈αcounterfactual␈αconditional␈αsentence␈α
␈↓↓If␈αits
␈↓ α∧␈↓↓intentions␈α
had␈α
been␈αdifferent␈α
the␈α
output␈αwouldn't␈α
have␈α
occurred␈↓,␈αand␈α
we␈α
require␈αwhat␈α
seems␈α
to␈αbe␈α
a
␈↓ α∧␈↓novel treatment of counterfactuals.

␈↓ α∧␈↓␈↓ αTWe␈α
treat␈α
the␈α
"relevant␈α
aspect␈α
of␈α
reality"␈α∞as␈α
a␈α
Cartesian␈α
product␈α
so␈α
that␈α
we␈α
can␈α∞talk␈α
about
␈↓ α∧␈↓changing␈α
one␈α
component␈α
and␈α
leaving␈α
the␈α
others␈α
unchanged.␈α
 This␈α
would␈α
be␈α
straightforward␈α
if␈α
the
␈↓ α∧␈↓Cartesian␈α∪product␈α∀structure␈α∪existed␈α∪in␈α∀the␈α∪world;␈α∀however,␈α∪it␈α∪usually␈α∀exists␈α∪only␈α∀in␈α∪certain
␈↓ α∧␈↓approximate␈αmodels␈α
of␈αthe␈α
world.␈α Consequently␈αno␈α
single␈αdefinite␈α
state␈αof␈αthe␈α
world␈αas␈α
a␈αwhole
␈↓ α∧␈↓corresponds␈αto␈αchanging␈αone␈αcomponent.␈α The␈α
following␈αparagraphs␈αpresent␈αthese␈αideas␈αin␈α
greater
␈↓ α∧␈↓detail.  a situation is character

␈↓ α∧␈↓␈↓ αTFor␈αexample,␈αsuppose␈α␈↓↓A␈↓␈αis␈αa␈αtheory␈α
in␈αwhich␈αsome␈αaspect␈αof␈αreality␈αis␈αcharacterized␈α
by␈αthe
␈↓ α∧␈↓values␈αof␈αthree␈αquantities␈α␈↓↓x,␈↓␈α␈↓↓y␈↓␈αand␈α␈↓↓z␈↓.␈α Let␈α␈↓↓f␈↓␈αbe␈αa␈αfunction␈αof␈αthree␈αarguments,␈αlet␈α␈↓↓u␈↓␈αbe␈αa␈αquantity
␈↓ α∧␈↓satisfying␈α
␈↓↓u_=_f(x,y,z)␈↓,␈α
where␈α␈↓↓f(1,1,1)_=_3␈↓␈α
and␈α
␈↓↓f(2,1,1)_=_5␈↓.␈α Consider␈α
a␈α
state␈αof␈α
the␈α
model␈αin
␈↓ α∧␈↓which␈α⊂␈↓↓x_=_1␈↓,␈α⊂␈↓↓y_=_1␈↓␈α⊂and␈α⊂␈↓↓z_=_1␈↓.␈α⊂ Within␈α⊂the␈α⊂theory␈α⊂␈↓↓A,␈↓␈α⊂the␈α⊂counterfactual␈α⊂conditional␈α⊂sentence
␈↓ α∧␈↓␈↓↓"u_=_3,␈α
but␈α
if␈α
x␈α
were␈α
2,␈α
then␈α
u␈α
would␈α
be␈α
5"␈↓␈α
is␈α
true,␈α
because␈α
the␈α
counterfactual␈α
condition␈αmeans
␈↓ α∧␈↓changing ␈↓↓x␈↓ to 2 and leaving the other variables unchanged.

␈↓ α∧␈↓␈↓ ε|8␈↓ ∧



␈↓ α∧␈↓␈↓ αTNow␈α
let's␈α
go␈α
beyond␈α
the␈αmodel␈α
and␈α
suppose␈α
that␈α
␈↓↓x,␈↓␈α
␈↓↓y␈↓␈αand␈α
␈↓↓z␈α
are␈↓␈α
quantities␈α
depending␈αon␈α
the
␈↓ α∧␈↓state␈αof␈αthe␈αworld.␈α Now␈αeven␈αif␈α␈↓↓u_=_f(x,y,z)␈↓␈αis␈αtaken␈αas␈αa␈αlaw␈αof␈αnature,␈αthe␈αcounterfactual␈αneed
␈↓ α∧␈↓not␈αbe␈αtaken␈αas␈αtrue,␈αbecause␈αsomeone␈αmight␈αargue␈αthat␈αif␈α␈↓↓x␈↓␈αwere␈α2,␈αthen␈α␈↓↓y␈↓␈αwould␈αbe␈α3␈αso␈αthat␈α␈↓↓u␈↓
␈↓ α∧␈↓might␈α∂not␈α∞be␈α∂5.␈α∞ However,␈α∂if␈α∂the␈α∞theory␈α∂␈↓↓A␈↓␈α∞has␈α∂a␈α∂sufficiently␈α∞preferred␈α∂status␈α∞we␈α∂may␈α∂take␈α∞the
␈↓ α∧␈↓meaning of the conunterfactual in ␈↓↓A␈↓ to be its general meaning.

␈↓ α∧␈↓␈↓ αTWe␈αsuggest␈αthat␈αthis␈αis␈αoften␈α(I␈αhaven't␈αyet␈αlooked␈αfor␈αcounter-examples)␈αthe␈αcommon␈αsense
␈↓ α∧␈↓meaning␈αof␈αa␈αcounterfactual.␈α The␈αcounterfactual␈αhas␈αa␈αdefinite␈αmeaning␈αin␈αa␈αtheory,␈αbecause␈αthe
␈↓ α∧␈↓theory␈αhas␈α
a␈αCartesian␈α
product␈αstructure,␈αand␈α
the␈αtheory␈α
is␈αsufficiently␈α
preferred␈αthat␈αthe␈α
meaning
␈↓ α∧␈↓of␈α
the␈α
counterfactual␈α
in␈α
the␈α
world␈α
is␈α
taken␈αas␈α
its␈α
meaning␈α
in␈α
the␈α
theory.␈α
 This␈α
is␈α
especially␈αlikely␈α
to
␈↓ α∧␈↓be␈αtrue␈αfor␈αconcepts␈αthat␈αhave␈αa␈αnatural␈αdefinition␈αin␈αterms␈αof␈αcounterfactuals,␈αe.g.␈αthe␈αconcept␈αof
␈↓ α∧␈↓␈↓↓deliberate action␈↓ with which we started this section.

␈↓ α∧␈↓␈↓ αTIn␈α∪all␈α∪cases␈α∀that␈α∪we␈α∪know␈α∀about,␈α∪the␈α∪theory␈α∪is␈α∀only␈α∪approximate␈α∪-␈α∀provided␈α∪certain
␈↓ α∧␈↓propositions␈α∪are␈α∪true␈α∪a␈α∪certain␈α∪quantity␈α∩is␈α∪approximately␈α∪a␈α∪given␈α∪function␈α∪of␈α∪certain␈α∩other
␈↓ α∧␈↓quantities.␈α This␈αmeans␈αthat␈αuseful␈αconcept␈αlike␈αdeliberate␈αaction␈αmay␈αseem␈αto␈αvanish␈αif␈αexamined
␈↓ α∧␈↓too closely, i.e. outside the limits of the theory within which it is defined.

␈↓ α∧␈↓Remarks:

␈↓ α∧␈↓␈↓ αT1.␈α
The␈α
known␈αcases␈α
in␈α
which␈α
a␈αconcept␈α
is␈α
defined␈α
relative␈αto␈α
an␈α
approximate␈αtheory␈α
involve
␈↓ α∧␈↓counterfactuals.  This may not always be the case.

␈↓ α∧␈↓␈↓ αT2. It is important to study the nature of the approximations.

␈↓ α∧␈↓␈↓ αT3.␈α(McCarthy␈αand␈αHayes␈α1969)␈αtreats␈αthe␈αnotion␈αof␈α␈↓↓X␈αcan␈αdo␈αY␈↓␈αusing␈αa␈αtheory␈αin␈αwhich␈αthe
␈↓ α∧␈↓world␈αis␈α
regarded␈αas␈αa␈α
collection␈αof␈α
interacting␈αautomata.␈α That␈α
paper␈αfailed␈α
to␈αnote␈αthat␈α
sentences
␈↓ α∧␈↓using ␈↓↓can␈↓ cannot necessarily be translated into single assertions about the world.

␈↓ α∧␈↓␈↓ αT4.␈α∞Old␈α∞fashioned␈α∞introspective␈α∂psychology␈α∞may␈α∞have␈α∞been␈α∞on␈α∂the␈α∞right␈α∞track␈α∞in␈α∂trying␈α∞to
␈↓ α∧␈↓analyze␈αthe␈αmind␈αinto␈αan␈αinteracting␈α␈↓↓will,␈↓␈α␈↓↓intellect␈↓␈αand␈αother␈αcomponents.␈α These␈αconcepts␈αmight
␈↓ α∧␈↓be precisely defined within a suitable approximate theory.

␈↓ α∧␈↓␈↓ αT5.␈α∩The␈α∩above␈α∩treatment␈α∩of␈α∩counterfactuals␈α∩in␈α∩which␈α∩they␈α∩are␈α∩defined␈α∩in␈α∩terms␈α∩of␈α∩the
␈↓ α∧␈↓Cartesian␈α⊃product␈α⊃structure␈α⊃of␈α⊂an␈α⊃approximate␈α⊃theory␈α⊃may␈α⊃be␈α⊂better␈α⊃than␈α⊃the␈α⊃␈↓↓closes␈α⊃state␈↓␈α⊂or
␈↓ α∧␈↓␈↓↓possible␈α
worlds␈↓␈α∞treatments␈α
discussed␈α
in␈α∞(Lewis␈α
1973).␈α
 The␈α∞truth-values␈α
are␈α
well␈α∞defined␈α
withing
␈↓ α∧␈↓the␈αapproximate␈αtheories,␈αand␈αthe␈αtheories␈αcan␈αbe␈αjustified␈αby␈αevidence␈αinvolving␈αphenomena␈αnot
␈↓ α∧␈↓mentioned in isolated counterfactual assertions.

␈↓ α∧␈↓␈↓ αT6.␈αIf,␈αas␈αwe␈αconjecture,␈αmost␈αcommon␈αsense␈αand␈αeven␈αscientific␈αterms␈αare␈αmeaningful␈αonly␈αin
␈↓ α∧␈↓approximate␈α∞theories,␈α∞then␈α∞a␈α∞philosophical␈α∞method␈α
as␈α∞old␈α∞as␈α∞Socrates␈α∞needs␈α∞to␈α∞be␈α
re-examined.
␈↓ α∧␈↓This␈α∞method␈α
involves␈α∞attacking␈α∞a␈α
common␈α∞sense␈α
notion␈α∞by␈α∞introducing␈α
examples␈α∞that␈α∞have␈α
not
␈↓ α∧␈↓been␈αencountered␈αin␈αthe␈αprevious␈αusage␈αof␈αthe␈αnotion␈αand␈αshowing␈αthat␈αin␈αthese␈αcases␈αthe␈αnotion
␈↓ α∧␈↓gives␈αunacceptable␈αresults.␈α But␈αit␈αmay␈αbe␈αthat␈αany␈αtheory␈αof␈α␈↓↓just␈↓␈αor␈α␈↓↓unjust␈↓␈αactions␈αmust␈αbe␈αbased
␈↓ α∧␈↓on␈αan␈αapproximate␈αmodel␈αof␈αthe␈αworld,␈αand␈αanomalies␈αcan␈αalways␈αbe␈αfound.␈α Thus␈αphilosophical
␈↓ α∧␈↓analysis␈α
cannot␈αinvalidate␈α
a␈α
notion␈αby␈α
finding␈α
limits␈αon␈α
its␈α
applicability;␈αthat␈α
requires␈α
a␈αbetter␈α
and
␈↓ α∧␈↓more␈αgeneral␈αnotion.␈α Even␈αwhen␈αfound,␈αthe␈αimproved␈αnotion␈αwill␈αstill␈αbe␈αlimited,␈αand␈αthere␈αmay


␈↓ α∧␈↓␈↓ ε|9␈↓ ∧



␈↓ α∧␈↓never␈α∞be␈α∂a␈α∞notion␈α∂of␈α∞just␈α∞action␈α∂founded␈α∞on␈α∂quantum␈α∞physics␈α∞and␈α∂chemistry.␈α∞ Notice␈α∂that␈α∞this
␈↓ α∧␈↓conclusion does not depend on considerations of ␈↓↓emergent␈↓ ␈↓↓phenomena.␈↓















































␈↓ α∧␈↓␈↓ εu10␈↓ ∧



␈↓ α∧␈↓α␈↓ βxEXAMPLES OF SYSTEMS WITH MENTAL QUALITIES

␈↓ α∧␈↓␈↓ αTLet␈α
us␈α
consider␈α
some␈αexamples␈α
of␈α
machines␈α
and␈α
programs␈αto␈α
which␈α
we␈α
may␈α
ascribe␈αbelief
␈↓ α∧␈↓and goal structures.

␈↓ α∧␈↓␈↓ αT1.␈α⊂ ␈↓αThermostats.␈↓␈α⊂Ascribing␈α⊂beliefs␈α⊂to␈α⊂simple␈α⊂thermostats␈α⊂is␈α⊂unnecessary␈α⊂for␈α⊂the␈α⊂study␈α∂of
␈↓ α∧␈↓thermostats,␈α⊃because␈α∩their␈α⊃operation␈α∩can␈α⊃be␈α⊃well␈α∩understood␈α⊃without␈α∩it.␈α⊃ However,␈α∩their␈α⊃very
␈↓ α∧␈↓simplicity␈α⊃makes␈α⊃it␈α∩clearer␈α⊃what␈α⊃is␈α⊃involved␈α∩in␈α⊃the␈α⊃ascription,␈α⊃and␈α∩we␈α⊃maintain␈α⊃(partly␈α∩as␈α⊃a
␈↓ α∧␈↓provocation␈αto␈αthose␈αwho␈αregard␈αattribution␈αof␈αbeliefs␈αto␈αmachines␈αas␈αmere␈αintellectual␈αsloppiness)
␈↓ α∧␈↓that the ascription is legitimate.␈↓∧7␈↓

␈↓ α∧␈↓␈↓ αTFirst␈αconsider␈αa␈αsimple␈αthermostat␈αthat␈αturns␈αoff␈αthe␈αheat␈αwhen␈αthe␈αtemperature␈αis␈αa␈αdegree
␈↓ α∧␈↓above␈αthe␈αtemperature␈αset␈αon␈αthe␈αthermostat,␈αturns␈αon␈αthe␈αheat␈αwhen␈αthe␈αtemperature␈αis␈αa␈αdegree
␈↓ α∧␈↓below␈α
the␈α
desired␈α
temperature,␈α
and␈α
leaves␈α
the␈α
heat␈α
as␈α
is␈α
when␈α
the␈α
temperature␈α
is␈α
in␈α
the␈α
two␈α
degree
␈↓ α∧␈↓range␈αaround␈αthe␈αdesired␈αtemperature.␈αThe␈αsimplest␈αbelief␈αpredicate␈α␈↓↓B(s,p)␈↓␈αascribes␈αbelief␈αto␈αonly
␈↓ α∧␈↓three␈α∂sentences:␈α∂"The␈α∂room␈α∂is␈α∂too␈α∂cold",␈α∂"The␈α∂room␈α∂is␈α∂too␈α∂hot",␈α∂and␈α∂"The␈α∂room␈α∂is␈α∂OK"␈α∂-␈α∞the
␈↓ α∧␈↓beliefs␈α⊃being␈α⊃assigned␈α⊃to␈α⊃states␈α⊃of␈α⊃the␈α⊃thermostat␈α⊃in␈α⊃the␈α⊃obvious␈α⊃way.␈α⊃ When␈α∩the␈α⊃thermostat
␈↓ α∧␈↓believes␈α
the␈α∞room␈α
is␈α
too␈α∞cold␈α
or␈α
too␈α∞hot,␈α
it␈α∞sends␈α
a␈α
message␈α∞saying␈α
so␈α
to␈α∞the␈α
furnace.␈α∞A␈α
slightly
␈↓ α∧␈↓more␈αcomplex␈αbelief␈α
predicate␈αcould␈αalso␈α
be␈αused␈αin␈α
which␈αthe␈αthermostat␈α
has␈αa␈αbelief␈αabout␈α
what
␈↓ α∧␈↓the␈αtemperature␈αshould␈αbe␈αand␈αanother␈αbelief␈αabout␈αwhat␈αit␈αis.␈α It␈αis␈αnot␈αclear␈αwhich␈αis␈αbetter,␈αbut
␈↓ α∧␈↓if␈αwe␈αwished␈α
to␈αconsider␈αpossible␈αerrors␈α
in␈αthe␈αthermometer,␈αthen␈α
we␈αwould␈αascribe␈α
beliefs␈αabout
␈↓ α∧␈↓what␈αthe␈α
temperature␈αis.␈αWe␈α
do␈αnot␈αascribe␈α
to␈αit␈αany␈α
other␈αbeliefs;␈αit␈α
has␈αno␈αopinion␈α
even␈αabout
␈↓ α∧␈↓whether␈α∞the␈α∞heat␈α∞is␈α∂on␈α∞or␈α∞off␈α∞or␈α∂about␈α∞the␈α∞weather␈α∞or␈α∞about␈α∂who␈α∞won␈α∞the␈α∞battle␈α∂of␈α∞Waterloo.
␈↓ α∧␈↓Moreover, it has no introspective beliefs, i.e.  it doesn't believe that it believes the room is too hot.

␈↓ α∧␈↓␈↓ αTThe␈α⊃temperature␈α⊂control␈α⊃system␈α⊂in␈α⊃my␈α⊃house␈α⊂may␈α⊃be␈α⊂described␈α⊃as␈α⊃follows:␈α⊂Thermostats
␈↓ α∧␈↓upstairs␈αand␈α
downstairs␈αtell␈α
the␈αcentral␈α
system␈αto␈αturn␈α
on␈αor␈α
shut␈αoff␈α
hot␈αwater␈α
flow␈αto␈αthese␈α
areas.
␈↓ α∧␈↓A␈α
central␈αwater-temperature␈α
thermostat␈α
tells␈αthe␈α
furnace␈α
to␈αturn␈α
on␈α
or␈αoff␈α
thus␈α
keeping␈αthe␈α
central
␈↓ α∧␈↓hot␈α∞water␈α∞reservoir␈α∂at␈α∞the␈α∞right␈α∞temperture.␈α∂ Recently␈α∞it␈α∞was␈α∞too␈α∂hot␈α∞upstairs,␈α∞and␈α∂the␈α∞question
␈↓ α∧␈↓arose␈αas␈αto␈αwhether␈αthe␈αupstairs␈αthermostat␈αmistakenly␈α␈↓↓believed␈↓␈αit␈αwas␈αtoo␈αcold␈αupstairs␈αor␈α
whether
␈↓ α∧␈↓the␈α∂furnace␈α∂thermostat␈α∂mistakenly␈α∂␈↓↓believed␈α∂␈↓␈α∂the␈α∂water␈α∂was␈α∂too␈α∂cold.␈α∂ It␈α∂turned␈α∂out␈α∂that␈α∞neither
␈↓ α∧␈↓mistake␈α⊂was␈α⊃made;␈α⊂the␈α⊃downstairs␈α⊂controller␈α⊃␈↓↓tried␈↓␈α⊂to␈α⊃turn␈α⊂off␈α⊃the␈α⊂flow␈α⊃of␈α⊂water␈α⊃but␈α⊂␈↓↓couldn't␈↓,
␈↓ α∧␈↓because␈α∞the␈α∞valve␈α∂was␈α∞stuck.␈α∞ The␈α∞plumber␈α∂came␈α∞once␈α∞and␈α∞found␈α∂the␈α∞trouble,␈α∞and␈α∂came␈α∞again
␈↓ α∧␈↓when␈α
a␈αreplacement␈α
valve␈α
was␈αordered.␈α
 Since␈αthe␈α
services␈α
of␈αplumbers␈α
are␈αincreasingly␈α
expensive,
␈↓ α∧␈↓and␈αmicrocomputers␈αare␈αincreasingly␈αcheap,␈αone␈αis␈αled␈αto␈αdesign␈αa␈αtemperature␈αcontrol␈αsystem␈αthat
␈↓ α∧␈↓would ␈↓↓know␈↓ a lot more about the thermal state of the house and its own state of health.

␈↓ α∧␈↓␈↓ αTIn␈αthe␈αfirst␈αplace,␈αwhile␈αthe␈αpresent␈αsystem␈α␈↓↓couldn't␈↓␈αturn␈αoff␈αthe␈αflow␈αof␈αhot␈α
water␈αupstairs,
␈↓ α∧␈↓there␈αis␈αno␈αreason␈αto␈αascribe␈αto␈αit␈αthe␈α␈↓↓knowledge␈↓␈αthat␈αit␈αcouldn't,␈αand␈α␈↓↓a␈αfortiori␈↓␈αit␈αhad␈αno␈αability␈αto
␈↓ α∧␈↓␈↓↓communicate␈↓␈α
this␈α
␈↓↓fact␈↓␈αor␈α
to␈α
take␈α
it␈αinto␈α
account␈α
in␈α
controlling␈αthe␈α
system.␈α
 A␈α
more␈αadvanced␈α
system
␈↓ α∧␈↓would␈α
know␈α
whether␈α
the␈α∞␈↓↓actions␈↓␈α
it␈α
␈↓↓attempted␈↓␈α
succeeded,␈α∞and␈α
it␈α
would␈α
communicate␈α∞failures␈α
and
␈↓ α∧␈↓adapt␈αto␈αthem.␈α (We␈αadapted␈αto␈αthe␈αfailure␈αby␈αturning␈αoff␈αthe␈αwhole␈αsystem␈αuntil␈αthe␈αwhole␈αhouse
␈↓ α∧␈↓cooled␈αoff␈αand␈αthen␈αletting␈αthe␈αtwo␈αparts␈αwarm␈αup␈αtogether.␈α The␈αpresent␈αsystem␈αhas␈αthe␈α␈↓↓physical
␈↓ α∧␈↓↓capability␈↓ of doing this even if it hasn't the ␈↓↓knowledge␈↓ or the ␈↓↓will␈↓.





␈↓ α∧␈↓␈↓ εu11␈↓ ∧



␈↓ α∧␈↓␈↓ αT2.␈α
␈↓αSelf-reproducing␈α∞intelligent␈α
configurations␈α∞in␈α
a␈α
cellular␈α∞automaton␈α
world.␈↓␈α∞A␈α
␈↓↓cellular␈↓
␈↓ α∧␈↓␈↓↓automaton␈↓␈αsystem␈αassigns␈αto␈αeach␈αvertex␈αin␈αa␈αcertain␈αgraph␈αa␈αfinite␈αautomaton.␈α The␈αstate␈αof␈αeach
␈↓ α∧␈↓automaton␈αat␈αtime␈α␈↓↓t+1␈↓␈αdepends␈αon␈αits␈αstate␈αat␈αtime␈α␈↓↓t␈↓␈αand␈αthe␈αstates␈αof␈αits␈αneighbors␈αat␈αtime␈α␈↓↓t␈↓.␈αThe
␈↓ α∧␈↓most␈αcommon␈α
graph␈αis␈α
the␈αarray␈α
of␈αpoints␈α
␈↓↓(x,y)␈↓␈αin␈α
the␈αplane␈α
with␈αinteger␈α
co-ordinates␈α␈↓↓x␈↓␈α
and␈α␈↓↓y.␈↓
␈↓ α∧␈↓An␈α
early␈αuse␈α
of␈αcellular␈α
automata␈αwas␈α
by␈α
von␈αNeumann␈α
(196?)␈αwho␈α
found␈αa␈α
27␈α
state␈αautomaton
␈↓ α∧␈↓whose␈α∂cells␈α∂could␈α∞be␈α∂initialized␈α∂into␈α∞a␈α∂self-reproducing␈α∂configuration␈α∞that␈α∂was␈α∂also␈α∂a␈α∞universal
␈↓ α∧␈↓computer.␈α The␈αbasic␈αautomaton␈αin␈αvon␈αNeumann's␈αsystem␈αhad␈αa␈αdistinguished␈αstate␈αcalled␈α0␈αand
␈↓ α∧␈↓a␈α∂point␈α∞in␈α∂state␈α∞0␈α∂whose␈α∞four␈α∂neighbors␈α∂were␈α∞also␈α∂in␈α∞that␈α∂state␈α∞would␈α∂remain␈α∞in␈α∂state␈α∂0.␈α∞ The
␈↓ α∧␈↓initial␈αconfigurations␈α
considered␈αhad␈αall␈α
but␈αa␈αfinite␈α
number␈αof␈αcells␈α
in␈αstate␈α0,␈α
and,␈αof␈αcourse,␈α
this
␈↓ α∧␈↓property would persist although the number of non-zero cells might grow indefinitely with time.

␈↓ α∧␈↓␈↓ αTThe␈α∂self-reproducing␈α∂system␈α∞used␈α∂the␈α∂states␈α∞of␈α∂a␈α∂long␈α∞strip␈α∂of␈α∂non-zero␈α∞cells␈α∂as␈α∂a␈α∞"tape"
␈↓ α∧␈↓containing␈α
instructions␈α∞to␈α
a␈α∞"universal␈α
constructor"␈α
configuration␈α∞that␈α
would␈α∞construct␈α
a␈α∞copy␈α
of
␈↓ α∧␈↓the␈αconfiguration␈αto␈αbe␈αreproduced␈αbut␈αwith␈αeach␈αcell␈αin␈αa␈αpassive␈αstate␈αthat␈αwould␈αpersist␈αas␈α
long
␈↓ α∧␈↓as␈α⊂its␈α⊂neighbors␈α⊂were␈α⊂also␈α⊂in␈α⊂passive␈α⊂states.␈α⊂ After␈α⊂the␈α⊂construction␈α⊂phase,␈α⊂the␈α⊂tape␈α⊃would␈α⊂be
␈↓ α∧␈↓copied␈αto␈α
make␈αthe␈αtape␈α
for␈αthe␈αnew␈α
machine,␈αand␈α
then␈αthe␈αnew␈α
system␈αwould␈αbe␈α
set␈αin␈αmotion␈α
by
␈↓ α∧␈↓activating␈α
one␈αof␈α
its␈αcells.␈α
The␈α
new␈αsystem␈α
would␈αthen␈α
move␈α
away␈αfrom␈α
its␈αmother␈α
and␈αthe␈α
process
␈↓ α∧␈↓would␈α∀start␈α∪over.␈α∀ The␈α∪purpose␈α∀of␈α∪the␈α∀design␈α∪was␈α∀to␈α∪demonstrate␈α∀that␈α∀arbitrarily␈α∪complex
␈↓ α∧␈↓configurations␈α∞could␈α∂be␈α∞self-reproducing␈α∂-␈α∞the␈α∞complexity␈α∂being␈α∞assured␈α∂by␈α∞also␈α∂requiring␈α∞that
␈↓ α∧␈↓they be universal computers.

␈↓ α∧␈↓␈↓ αTSince␈α_von␈α↔Neumann's␈α_time,␈α↔simpler␈α_basic␈α↔cells␈α_admitting␈α_self-reproducing␈α↔universal
␈↓ α∧␈↓computers␈α∞have␈α∞been␈α∞discovered.␈α∂ The␈α∞simplest␈α∞so␈α∞far␈α∞is␈α∂the␈α∞two␈α∞state␈α∞Life␈α∞automaton␈α∂of␈α∞John
␈↓ α∧␈↓Conway␈α(196?).␈α
 The␈αstate␈α
of␈αa␈α
cell␈αat␈α
time␈α␈↓↓t+1␈↓␈α
is␈αdetermined␈α
its␈αstate␈α
at␈αtime␈α
␈↓↓t␈↓␈αand␈α
the␈αstates␈αof␈α
its
␈↓ α∧␈↓eight␈α
neighbors␈α
at␈α
time␈α
␈↓↓t.␈↓␈α
Namely,␈α
a␈α
point␈α
whose␈α
state␈α
is␈α
0␈α
will␈α
change␈α
to␈α
state␈α
1␈α
if␈α
exactly␈α
three␈α
of
␈↓ α∧␈↓its␈αneighbors␈αare␈αin␈αstate␈α1.␈α A␈αpoint␈αwhose␈αstate␈αis␈α1␈αwill␈αremain␈αin␈αstate␈α1␈αif␈αtwo␈αor␈αthree␈αof␈αits
␈↓ α∧␈↓neighbors are in state 1.  In all other cases the state becomes or remains 0.

␈↓ α∧␈↓␈↓ αTConway's␈αinitial␈αintent␈αwas␈αto␈αmodel␈αa␈αbirth␈αand␈αdeath␈αprocess␈αwhereby␈αa␈αcell␈αis␈αborn␈α(goes
␈↓ α∧␈↓into␈αstate␈α1)␈αif␈αit␈αhas␈α
the␈αright␈αnumber␈αof␈αliving␈αneighbors␈α
(namely␈αthree)␈αand␈αdies␈αif␈αit␈α
is␈αeither
␈↓ α∧␈↓too␈α⊂lonely␈α⊂(has␈α⊂none␈α⊂or␈α⊂one␈α⊂neighbor␈α⊂in␈α⊂state␈α⊂1)␈α⊂or␈α⊂is␈α⊂overcrowded␈α⊂(has␈α⊂four␈α⊂or␈α⊂more␈α∂living
␈↓ α∧␈↓neighbors).␈α∞ He␈α∞also␈α∞asked␈α∞whether␈α∞infinitely␈α∞growing␈α∞configurations␈α∞were␈α∞possible,␈α∞and␈α∞Gosper
␈↓ α∧␈↓first␈αproved␈αthat␈αthere␈αwere.␈α More␈αand␈αmore␈αinteresting␈α␈↓↓Life␈↓␈αconfigurations␈αwere␈αdiscovered,␈αand
␈↓ α∧␈↓surprisingly,␈αConway␈αand␈αGosper␈αhave␈αshown␈αthat␈αself-reproducing␈αuniversal␈αcomputers␈αcould␈α
be
␈↓ α∧␈↓built up as Life configurations.

␈↓ α∧␈↓␈↓ αTConsider␈α⊃a␈α⊂number␈α⊃of␈α⊂such␈α⊃self-reproducing␈α⊂universal␈α⊃computers␈α⊂operating␈α⊃in␈α⊃the␈α⊂Life
␈↓ α∧␈↓plane,␈αand␈α
suppose␈αthat␈α
they␈αhave␈α
been␈αprogrammed␈αto␈α
study␈αthe␈α
properties␈αof␈α
their␈αworld␈αand␈α
to
␈↓ α∧␈↓communicate␈α∩among␈α∩themselves␈α∪about␈α∩it,␈α∩perhaps␈α∪pursuing␈α∩various␈α∩goals␈α∪co-operatively␈α∩and
␈↓ α∧␈↓competitively.␈α∞ Call␈α
these␈α∞configurations␈α∞robots.␈α
 In␈α∞some␈α∞respects␈α
their␈α∞intellectual␈α∞and␈α
scientific
␈↓ α∧␈↓problems␈αwill␈αbe␈αlike␈αours,␈αbut␈αin␈αone␈αmajor␈αrespect␈αthey␈αlive␈αin␈αa␈αsimpler␈αworld␈αthan␈αours␈αseems
␈↓ α∧␈↓to␈αbe.␈α Namely,␈αthe␈αfundamental␈αphysics␈αof␈αtheir␈αworld␈αis␈αthat␈αof␈αthe␈αlife␈αautomaton,␈αand␈αthere␈αis
␈↓ α∧␈↓no␈αobstacle␈αto␈αeach␈αrobot␈α␈↓↓knowing␈↓␈αthis␈αphysics,␈αand␈αbeing␈αable␈αto␈αsimulate␈αthe␈αevolution␈αof␈αa␈αlife
␈↓ α∧␈↓configuration␈α
given␈α
the␈α
initial␈α
state.␈α
 Moreover,␈α
if␈α
the␈α
initial␈α
state␈α
of␈α
the␈α
robot␈α
world␈α
is␈α∞finite␈α
it
␈↓ α∧␈↓can␈α
have␈αbeen␈α
recorded␈αin␈α
each␈α
robot␈αin␈α
the␈αbeginning␈α
or␈αelse␈α
recorded␈α
on␈αa␈α
strip␈αof␈α
cells␈αthat␈α
the
␈↓ α∧␈↓robots␈α⊂can␈α⊃read.␈α⊂ (The␈α⊂infinite␈α⊃regress␈α⊂of␈α⊂having␈α⊃to␈α⊂describe␈α⊂the␈α⊃description␈α⊂is␈α⊂avoided␈α⊃by␈α⊂a
␈↓ α∧␈↓convention␈α
that␈α
the␈α
description␈α
is␈α
not␈α
separately␈α
described,␈α
but␈α
can␈α
be␈α
read␈α
␈↓↓both␈↓␈α
as␈α
a␈α
description␈α
of
␈↓ α∧␈↓the world ␈↓↓and␈↓ as a description of itself.)

␈↓ α∧␈↓␈↓ εu12␈↓ ∧



␈↓ α∧␈↓␈↓ αTSince␈α∂these␈α∂robots␈α∞know␈α∂the␈α∂initial␈α∞state␈α∂of␈α∂their␈α∞world␈α∂and␈α∂its␈α∞laws␈α∂of␈α∂motion,␈α∂they␈α∞can
␈↓ α∧␈↓simulate␈α∪as␈α∩much␈α∪of␈α∪their␈α∩world's␈α∪history␈α∩as␈α∪they␈α∪want,␈α∩assuming␈α∪that␈α∩each␈α∪can␈α∪grow␈α∩into
␈↓ α∧␈↓unoccupied␈α∞space␈α∞so␈α∞as␈α∞to␈α∞have␈α∞memory␈α∞to␈α∞store␈α∞the␈α∞states␈α∞of␈α∞the␈α∞world␈α∞being␈α∞simulated.␈α
 This
␈↓ α∧␈↓simulation␈α
is␈α
necessarily␈α
much␈α
slower␈αthan␈α
real␈α
time,␈α
so␈α
they␈α
can␈αnever␈α
catch␈α
up␈α
with␈α
the␈αpresent␈α
-
␈↓ α∧␈↓let␈α∞alone␈α∞predict␈α∞the␈α∞future.␈α∞ This␈α∞seems␈α∞obvious␈α
if␈α∞we␈α∞imagine␈α∞the␈α∞simulation␈α∞carried␈α∞out␈α∞in␈α
a
␈↓ α∧␈↓straightforwardly␈α
by␈α
updating␈α
a␈α
list␈α
of␈α
currently␈α
active␈α
cells␈α
in␈α
the␈α
simulated␈α
world␈α
according␈αto
␈↓ α∧␈↓the␈αLife␈αrule,␈αbut␈αit␈αalso␈αapplies␈αto␈αany␈αclever␈αmathematical␈αmethod␈αthat␈αmight␈αpredict␈αmillions␈αof
␈↓ α∧␈↓steps␈αahead.␈α (Some␈α
Life␈αconfigurations,␈αe.g.␈αstatic␈α
ones␈αor␈αones␈α
containing␈αsingle␈α␈↓↓gliders␈↓␈αor␈α
␈↓↓cannon␈↓
␈↓ α∧␈↓can␈αhave␈α
their␈αdistant␈α
futures␈αpredicted␈αwith␈α
little␈αcomputing.)␈α
Namely,␈αif␈α
there␈αwere␈αan␈α
algorithm
␈↓ α∧␈↓for␈α
such␈αprediction,␈α
a␈α
robot␈αcould␈α
be␈α
made␈αthat␈α
would␈α
predict␈αits␈α
own␈α
future␈αand␈α
then␈αdisobey␈α
the
␈↓ α∧␈↓prediction.␈α∞ The␈α
detailed␈α∞proof␈α
would␈α∞be␈α∞analogous␈α
to␈α∞the␈α
proof␈α∞of␈α
unsolvability␈α∞of␈α∞the␈α
halting
␈↓ α∧␈↓problem for Turing machines.

␈↓ α∧␈↓␈↓ αTNow␈α
we␈αcome␈α
to␈α
the␈αpoint␈α
of␈α
this␈αlong␈α
disquisition.␈α
 Suppose␈αwe␈α
wish␈α
to␈αprogram␈α
a␈αrobot␈α
to
␈↓ α∧␈↓be␈αsuccessful␈αin␈αthe␈αLife␈αworld␈αin␈αcompetition␈αor␈αco-operation␈αwith␈αthe␈αothers.␈α Without␈αany␈αidea
␈↓ α∧␈↓of␈αhow␈αto␈αgive␈αa␈αmathematical␈αproof,␈αI␈αwill␈αclaim␈αthat␈αour␈αrobot␈αwill␈αneed␈αprograms␈α
that␈αascribe
␈↓ α∧␈↓purposes␈α∂and␈α∂beliefs␈α∞to␈α∂its␈α∂fellow␈α∞robots␈α∂and␈α∂predict␈α∂how␈α∞they␈α∂will␈α∂react␈α∞to␈α∂its␈α∂own␈α∂actions␈α∞by
␈↓ α∧␈↓assuming␈α∂that␈α∂␈↓↓they␈α∞will␈α∂act␈α∂in␈α∞ways␈α∂that␈α∂they␈α∞believe␈α∂will␈α∂achieve␈α∞their␈α∂goals␈↓.␈α∂ Our␈α∂robot␈α∞might
␈↓ α∧␈↓acquire␈α
these␈α
mental␈α
theories␈αin␈α
several␈α
ways:␈α
First,␈α
we␈αmight␈α
design␈α
the␈α
universal␈α
machine␈αso␈α
that
␈↓ α∧␈↓they␈αare␈αpresent␈α
in␈αthe␈αinitial␈α
configuration␈αof␈αthe␈α
world.␈α Second,␈αwe␈α
might␈αprogram␈αit␈αto␈α
acquire
␈↓ α∧␈↓this␈α∪ideas␈α∀by␈α∪induction␈α∪from␈α∀its␈α∪experience␈α∪and␈α∀even␈α∪transmit␈α∪them␈α∀to␈α∪others␈α∀through␈α∪an
␈↓ α∧␈↓"educational␈αsystem".␈α Third,␈αit␈αmight␈αderive␈αthe␈αpsychological␈αlaws␈αfrom␈αthe␈αfundamental␈αphysics
␈↓ α∧␈↓of␈α∞the␈α∂world␈α∞and␈α∂its␈α∞knowledge␈α∂of␈α∞the␈α∂initial␈α∞configuration,␈α∂and␈α∞finally,␈α∂it␈α∞might␈α∂discover␈α∞how
␈↓ α∧␈↓robots are built from Life cells by doing experimental "biology".

␈↓ α∧␈↓␈↓ αTKnowing␈α∩the␈α∩Life␈α∩physics␈α∩without␈α∪some␈α∩information␈α∩about␈α∩the␈α∩initial␈α∪configuration␈α∩is
␈↓ α∧␈↓insufficient␈α
to␈α
derive␈α
the␈α␈↓↓psychological␈↓␈α
laws,␈α
because␈α
robots␈α
can␈αbe␈α
constructed␈α
in␈α
the␈α
Life␈αworld␈α
in
␈↓ α∧␈↓an␈αinfinity␈αof␈αways.␈α This␈αfollows␈αfrom␈αthe␈α"folk␈αtheorem"␈αthat␈αthe␈αLife␈αautomaton␈αis␈αuniversal␈αin
␈↓ α∧␈↓the␈α∞sense␈α∞that␈α∞any␈α
cellular␈α∞automaton␈α∞can␈α∞be␈α∞constructed␈α
by␈α∞taking␈α∞sufficiently␈α∞large␈α∞squares␈α
of
␈↓ α∧␈↓Life cells as the basic cell of the other automaton.␈↓∧8␈↓

␈↓ α∧␈↓␈↓ αTMen␈α⊂are␈α⊃in␈α⊂a␈α⊂more␈α⊃difficult␈α⊂intellectual␈α⊂position␈α⊃than␈α⊂Life␈α⊂robots.␈α⊃ We␈α⊂don't␈α⊃know␈α⊂the
␈↓ α∧␈↓fundamental␈α⊂physics␈α⊂of␈α∂our␈α⊂world,␈α⊂and␈α⊂we␈α∂can't␈α⊂even␈α⊂be␈α⊂sure␈α∂that␈α⊂its␈α⊂fundamental␈α⊂physics␈α∂is
␈↓ α∧␈↓describable␈α∂in␈α∂finite␈α⊂terms.␈α∂ Even␈α∂if␈α∂we␈α⊂knew␈α∂the␈α∂physical␈α∂laws,␈α⊂they␈α∂seem␈α∂to␈α⊂preclude␈α∂precise
␈↓ α∧␈↓knowledge␈α∞of␈α
an␈α∞initial␈α∞state␈α
and␈α∞precise␈α∞calculation␈α
of␈α∞its␈α∞future␈α
both␈α∞for␈α∞quantum␈α
mechanical
␈↓ α∧␈↓reasons␈α∩and␈α⊃because␈α∩the␈α∩continuous␈α⊃functions␈α∩needed␈α⊃to␈α∩represent␈α∩fields␈α⊃seem␈α∩to␈α∩involve␈α⊃an
␈↓ α∧␈↓infinite amount of information.

␈↓ α∧␈↓␈↓ αTOne␈αpoint␈αof␈αthe␈αcellular␈αautomaton␈αrobot␈αexample␈αis␈αto␈αmake␈αplausible␈αthe␈αidea␈αthat␈α
much
␈↓ α∧␈↓of␈α
human␈α
mental␈αstructure␈α
is␈α
not␈α
an␈αaccident␈α
of␈α
evolution␈αor␈α
even␈α
of␈α
the␈αphysics␈α
of␈α
our␈αworld,␈α
but
␈↓ α∧␈↓is␈αrequired␈αfor␈αsuccessful␈αproblem␈αsolving␈αbehavior␈αand␈αmust␈αbe␈αdesigned␈αinto␈αor␈αevolved␈αby␈αany
␈↓ α∧␈↓system that exhibits such behavior.



␈↓ α∧␈↓␈↓ αT3.␈α→␈↓αComputer␈α→time-sharing␈α→systems.␈↓␈α→These␈α→complicated␈α→computer␈α→programs␈α_allocate
␈↓ α∧␈↓computer␈αtime␈αand␈α
other␈αresources␈αamong␈α
users.␈α They␈αallow␈α
each␈αuser␈αof␈α
the␈αcomputer␈αto␈α
behave


␈↓ α∧␈↓␈↓ εu13␈↓ ∧



␈↓ α∧␈↓as␈αthough␈αhe␈α
had␈αa␈αcomputer␈αof␈α
his␈αown,␈αbut␈αalso␈α
allow␈αthem␈αto␈αshare␈α
files␈αof␈αdata␈αand␈α
programs
␈↓ α∧␈↓and␈α
to␈α
communicate␈α
with␈α
each␈α
other.␈α
 They␈α
are␈α
often␈α
used␈α
for␈α
many␈α
years␈α
with␈α∞continual␈α
small
␈↓ α∧␈↓changes,␈α
and␈α
and␈α∞the␈α
people␈α
making␈α∞the␈α
changes␈α
and␈α
correcting␈α∞errors␈α
are␈α
often␈α∞different␈α
from
␈↓ α∧␈↓the␈αoriginal␈αauthors␈αof␈αthe␈αsystem.␈α A␈α
person␈αconfronted␈αwith␈αthe␈αtask␈αof␈αcorrecting␈αa␈α
malfunction
␈↓ α∧␈↓or␈α
making␈α
a␈α
change␈α∞in␈α
a␈α
time-sharing␈α
system␈α
often␈α∞can␈α
conveniently␈α
use␈α
a␈α
mentalistic␈α∞model␈α
of
␈↓ α∧␈↓the system.

␈↓ α∧␈↓␈↓ αTThus␈α⊂suppose␈α∂a␈α⊂user␈α∂complains␈α⊂that␈α⊂the␈α∂system␈α⊂will␈α∂not␈α⊂run␈α∂his␈α⊂program.␈α⊂ Perhaps␈α∂the
␈↓ α∧␈↓system␈αbelieves␈α
that␈αhe␈αdoesn't␈α
want␈αto␈α
run,␈αperhaps␈αit␈α
persistently␈αbelieves␈αthat␈α
he␈αhas␈α
just␈αrun,
␈↓ α∧␈↓perhaps␈αit␈αbelieves␈αthat␈αhis␈αquota␈αof␈αcomputer␈αresources␈αis␈αexhausted,␈αor␈αperhaps␈αit␈αbelieves␈αthat
␈↓ α∧␈↓his␈αprogram␈αrequires␈αa␈αresource␈αthat␈αis␈αunavailable.␈α Testing␈αthese␈αhypotheses␈αcan␈αoften␈α
be␈αdone
␈↓ α∧␈↓with surprisingly little understanding of the internal workings of the program.



␈↓ α∧␈↓␈↓ αT4.␈α∩␈↓αPrograms␈α⊃designed␈α∩to␈α⊃reason.␈↓␈α∩Suppose␈α∩we␈α⊃explicitly␈α∩design␈α⊃a␈α∩program␈α∩to␈α⊃represent
␈↓ α∧␈↓information␈αby␈αsentences␈αin␈αa␈αcertain␈αlanguage␈αstored␈αin␈αthe␈αmemory␈αof␈αthe␈αcomputer␈αand␈αdecide
␈↓ α∧␈↓what␈αto␈α
do␈αby␈α
making␈αinferences,␈αand␈α
doing␈αwhat␈α
it␈αconcludes␈αwill␈α
advance␈αits␈α
goals.␈α Naturally,
␈↓ α∧␈↓we␈αwould␈αhope␈α
that␈αour␈αprevious␈α
second␈αorder␈αdefinition␈α
of␈αbelief␈αwill␈α
"approve␈αof"␈αa␈α␈↓↓B(p,s)␈↓␈α
that
␈↓ α∧␈↓ascribed␈α∩to␈α∩the␈α⊃program␈α∩believing␈α∩the␈α⊃sentences␈α∩explicitly␈α∩built␈α⊃in.␈α∩ We␈α∩would␈α∩be␈α⊃somewhat
␈↓ α∧␈↓embarassed␈αif␈αsomeone␈αwere␈αto␈αshow␈αthat␈α
our␈αsecond␈αorder␈αdefinition␈αapproved␈αas␈αwell␈α
or␈αbetter
␈↓ α∧␈↓of an entirely different set of beliefs.

␈↓ α∧␈↓␈↓ αTSuch a program was first proposed in (McCarthy 1959), and here is how it might work:

␈↓ α∧␈↓␈↓ αTInformation␈αabout␈αthe␈αworld␈αis␈αstored␈αin␈αa␈αwide␈αvariety␈αof␈αdata␈αstructures.␈α For␈αexample,␈αa
␈↓ α∧␈↓visual␈α∂scene␈α∂received␈α∂by␈α∂a␈α∂TV␈α∂camera␈α∂may␈α∂be␈α∂represented␈α∂by␈α∂a␈α∂512x512x3␈α∂array␈α⊂of␈α∂numbers
␈↓ α∧␈↓representing␈αthe␈αintensities␈αof␈αthree␈α
colors␈αat␈αthe␈αpoints␈αof␈α
the␈αvisual␈αfield.␈α At␈αanother␈α
level,␈αthe
␈↓ α∧␈↓same␈αscene␈α
may␈αbe␈α
represented␈αby␈α
a␈αlist␈α
of␈αregions,␈αand␈α
at␈αa␈α
further␈αlevel␈α
there␈αmay␈α
be␈αa␈α
list␈αof
␈↓ α∧␈↓physical␈α
objects␈α
and␈αtheir␈α
parts␈α
together␈αwith␈α
other␈α
information␈αabout␈α
these␈α
objects␈αobtained␈α
from
␈↓ α∧␈↓non-visual␈αsources.␈α Moreover,␈αinformation␈αabout␈αhow␈α
to␈αsolve␈αvarious␈αkinds␈αof␈αproblems␈αmay␈α
be
␈↓ α∧␈↓represented by programs in some programming language.

␈↓ α∧␈↓␈↓ αTHowever,␈α⊂all␈α⊂the␈α⊂above␈α∂representations␈α⊂are␈α⊂subordinate␈α⊂to␈α∂a␈α⊂collection␈α⊂of␈α⊂sentences␈α⊂in␈α∂a
␈↓ α∧␈↓suitable␈α∂first␈α∂order␈α∂language␈α∞that␈α∂includes␈α∂set␈α∂theory.␈α∂ By␈α∞subordinate,␈α∂we␈α∂mean␈α∂that␈α∂there␈α∞are
␈↓ α∧␈↓sentences␈α
that␈α
tell␈α
what␈α
the␈α
data␈α
structures␈α
represent␈α
and␈α
what␈α
the␈α
programs␈α
do.␈α
 New␈αsentences
␈↓ α∧␈↓can␈αarise␈αby␈αa␈αvariety␈αof␈αprocesses:␈αinference␈αfrom␈αsentences␈αalready␈αpresent,␈αby␈αcomputation␈αfrom
␈↓ α∧␈↓the␈α∨data␈α∨structures␈α∨representing␈α∨observations,␈α∨and␈α∨by␈α∨interpreting␈α∨certain␈α inputs␈α∨as
␈↓ α∧␈↓communications in a one or more languages.

␈↓ α∧␈↓␈↓ αTThe␈αconstruction␈αof␈α
such␈αa␈αprogram␈αis␈α
one␈αof␈αthe␈αmajor␈α
approaches␈αto␈αachieving␈αhigh␈α
level
␈↓ α∧␈↓artificial␈αintelligence,␈αand,␈αlike␈αevery␈αother␈αapproach,␈αit␈αfaces␈αnumerous␈αobstacles.␈α These␈αobstacles
␈↓ α∧␈↓can␈αbe␈αdivided␈αinto␈αtwo␈αclasses␈α-␈α␈↓↓epistemological␈αand␈↓␈α␈↓↓heuristic.␈↓␈αThe␈αepistemological␈αproblem␈αis␈αto
␈↓ α∧␈↓determine␈αwhat␈αinformation␈αabout␈αthe␈αworld␈αis␈αto␈αbe␈αrepresented␈αin␈αthe␈αsentences␈αand␈αother␈αdata
␈↓ α∧␈↓structures,␈α
and␈αthe␈α
heuristic␈αproblem␈α
is␈αto␈α
decide␈αhow␈α
the␈αinformation␈α
can␈αbe␈α
used␈α
effectively␈αto
␈↓ α∧␈↓solve␈α∞problems.␈α∞ Naturally,␈α∞the␈α∞problems␈α∞interact,␈α
but␈α∞the␈α∞epistemological␈α∞problem␈α∞is␈α∞more␈α
basic
␈↓ α∧␈↓and␈αalso␈αmore␈αrelevant␈αto␈αour␈αpresent␈αconcerns.␈α We␈αcould␈αregard␈αit␈αas␈αsolved␈αif␈αwe␈αknew␈αhow␈αto


␈↓ α∧␈↓␈↓ εu14␈↓ ∧



␈↓ α∧␈↓express␈αthe␈αinformation␈αneeded␈α
for␈αintelligent␈αbehavior␈αso␈α
that␈αthe␈αsolution␈αto␈α
problems␈αlogically
␈↓ α∧␈↓followed from the data.  The heuristic problem of actually obtaining the solutions would remain.

␈↓ α∧␈↓␈↓ αTThe␈α
information␈αto␈α
be␈αrepresented␈α
can␈α
be␈αroughly␈α
divided␈αinto␈α
general␈α
information␈αabout
␈↓ α∧␈↓the␈α⊗world␈α↔and␈α⊗information␈α⊗about␈α↔particular␈α⊗situations.␈α⊗ The␈α↔formalism␈α⊗used␈α↔to␈α⊗represent
␈↓ α∧␈↓information␈α∪about␈α∪the␈α∪world␈α∪must␈α∪be␈α∪␈↓↓epistemologically␈↓␈α∪␈↓↓adequate,␈↓␈α∪i.e.␈α∪it␈α∪must␈α∪be␈α∪capable␈α∪of
␈↓ α∧␈↓representing␈αthe␈αinformation␈αthat␈αis␈αactually␈αavailable␈αto␈αthe␈αprogram␈αfrom␈αits␈α
sensory␈αapparatus
␈↓ α∧␈↓or␈αcan␈αbe␈αdeduced.␈α Thus␈αit␈αcouldn't␈αhandle␈α
available␈αinformation␈αabout␈αa␈αcup␈αof␈αhot␈αcoffee␈αif␈α
its
␈↓ α∧␈↓only␈αway␈αof␈αrepresenting␈αinformation␈αabout␈αfluids␈αwas␈αin␈αterms␈αof␈αthe␈αpositions␈αand␈α
velocities␈αof
␈↓ α∧␈↓the␈αmolecules.␈α Even␈αthe␈αhydrodynamicist's␈αEulerian␈αdistributions␈αof␈αdensity,␈αvelocity,␈αtemperature
␈↓ α∧␈↓and␈α∀pressure␈α∪would␈α∀be␈α∪useless␈α∀for␈α∪representing␈α∀the␈α∪information␈α∀actually␈α∪obtainable␈α∀from␈α∪a
␈↓ α∧␈↓television camera.  These considerations are further discussed in (McCarthy and Hayes 1969).

␈↓ α∧␈↓␈↓ αTHere are some of the kinds of general information that will have to be represented:

␈↓ α∧␈↓␈↓ αT1.␈α∃Partial␈α∃information␈α∃about␈α∃causal␈α∃systems.␈α∃ Quantities␈α∃have␈α∃values␈α∃and␈α∃later␈α∃have
␈↓ α∧␈↓different values.  Causal laws relate these values.

␈↓ α∧␈↓␈↓ αT2.␈αSome␈αchanges␈αare␈αresults␈αof␈αactions␈αby␈αthe␈αprogram␈αand␈αother␈αactors.␈α Information␈αabout
␈↓ α∧␈↓the effects of actions can be used to determine what goals can be achieved in given circumstances.

␈↓ α∧␈↓␈↓ αT3.␈αObjects␈αand␈αsubstances␈αare␈αhave␈αlocations␈αin␈αspace.␈α It␈αmay␈αbe␈αthat␈αtemporal␈αand␈αcausal
␈↓ α∧␈↓facts are prior to spatial in the formalism.

␈↓ α∧␈↓␈↓ αT4. Some objects are actors with beliefs, purposes and intentions.

␈↓ α∧␈↓␈↓ αTOf␈α∞course,␈α∞the␈α
above␈α∞English␈α∞description␈α
is␈α∞no␈α∞substitute␈α
for␈α∞an␈α∞axiomatized␈α∞formalism␈α
-
␈↓ α∧␈↓not␈α⊂even␈α⊂for␈α⊃philosophy␈α⊂but␈α⊂␈↓↓a␈α⊃fortiori␈↓␈α⊂when␈α⊂computer␈α⊂programs␈α⊃must␈α⊂be␈α⊂written.␈α⊃ The␈α⊂main
␈↓ α∧␈↓difficulties␈α∞in␈α∂designing␈α∞such␈α∞a␈α∂formalism␈α∞involve␈α∞deciding␈α∂how␈α∞to␈α∞express␈α∂partial␈α∞information.
␈↓ α∧␈↓(McCarthy␈α∞and␈α∞Hayes␈α∞1970)␈α∞uses␈α∞a␈α∞notion␈α∂of␈α∞␈↓↓situation␈↓␈α∞wherein␈α∞the␈α∞situation␈α∞is␈α∞never␈α∂known␈α∞-
␈↓ α∧␈↓only␈αfacts␈αabout␈αsituations␈αare␈αknown.␈α Unfortunately,␈αthe␈αformalism␈αis␈αnot␈αsuitable␈αfor␈α
expressing
␈↓ α∧␈↓what␈αmight␈αbe␈αknown␈αwhen␈αevents␈αare␈αtaking␈αplace␈αin␈αparallel␈αwith␈αunknown␈αtemporal␈αrelations.
␈↓ α∧␈↓It␈α⊃also␈α⊃only␈α⊃treats␈α⊃the␈α⊃case␈α⊃in␈α⊃which␈α⊃the␈α⊂result␈α⊃of␈α⊃an␈α⊃action␈α⊃is␈α⊃a␈α⊃definite␈α⊃new␈α⊃situation␈α⊂and
␈↓ α∧␈↓therefore is isn't suitable for describing continuous processes.















␈↓ α∧␈↓␈↓ εu15␈↓ ∧



␈↓ α∧␈↓α␈↓ ∧j"GLOSSARY" OF MENTAL QUALITIES

␈↓ α∧␈↓␈↓ αTIn␈α
this␈α
section␈α
we␈α∞give␈α
short␈α
"definitions"␈α
for␈α
machines␈α∞of␈α
a␈α
collection␈α
of␈α∞mental␈α
qualities.
␈↓ α∧␈↓We␈αinclude␈αa␈αnumber␈αof␈α
terms␈αwhich␈αgive␈αus␈αdifficulty␈α
with␈αan␈αindication␈αof␈αwhat␈αthe␈α
difficulties
␈↓ α∧␈↓seem to be.

␈↓ α∧␈↓␈↓ αT1.␈α
␈↓αActions␈↓.␈α
 We␈α
want␈α
to␈α
distinguish␈α
the␈α
actions␈α
of␈α
a␈α
being␈α
from␈α
events␈α
that␈α
occur␈α
in␈α
its␈α
body
␈↓ α∧␈↓and␈α
that␈αaffect␈α
the␈α
outside␈αworld.␈α
 For␈α
example,␈αwe␈α
wish␈αto␈α
distinguish␈α
a␈αrandom␈α
twitch␈α
from␈αa
␈↓ α∧␈↓purposeful␈α∞movement.␈α
 This␈α∞is␈α
not␈α∞difficult␈α
␈↓↓relative␈α∞to␈α
a␈α∞theory␈α
of␈α∞belief␈α
that␈α∞includes␈α
intentions␈↓.
␈↓ α∧␈↓One's␈α⊂purposeful␈α⊃actions␈α⊂are␈α⊂those␈α⊃that␈α⊂would␈α⊃have␈α⊂been␈α⊂different␈α⊃had␈α⊂one's␈α⊃intentions␈α⊂been
␈↓ α∧␈↓different.␈α∞ This␈α
requires␈α∞that␈α
the␈α∞theory␈α
of␈α∞belief␈α
have␈α∞sufficient␈α
Cartesian␈α∞product␈α∞structure␈α
so
␈↓ α∧␈↓that␈αthe␈αcounterfactual␈αconditional␈α`"if␈αits␈α
intentions␈αhad␈αbeen␈αdifferent"␈αis␈αdefined␈αin␈α
the␈αtheory.
␈↓ α∧␈↓As␈α
explained␈α
in␈α∞the␈α
section␈α
on␈α
definitions␈α∞relative␈α
to␈α
an␈α
approximate␈α∞theory,␈α
it␈α
is␈α∞not␈α
necessary
␈↓ α∧␈↓that the counterfactual be given a meaning in terms of the real world.

␈↓ α∧␈↓␈↓ αT2.␈α␈↓αIntrospection␈αand␈αself-knowledge␈↓.␈α We␈αsay␈α
that␈αa␈αmachine␈αintrospects␈αwhen␈αit␈α
comes␈αto
␈↓ α∧␈↓have␈α⊃beliefs␈α⊂about␈α⊃its␈α⊃own␈α⊂mental␈α⊃state.␈α⊂ A␈α⊃simple␈α⊃form␈α⊂of␈α⊃introspection␈α⊂takes␈α⊃place␈α⊃when␈α⊂a
␈↓ α∧␈↓program␈αdetermines␈αwhether␈α
it␈αhas␈αcertain␈αinformation␈α
and␈αif␈αnot␈αasks␈α
for␈αit.␈α Often␈αan␈α
operating
␈↓ α∧␈↓system␈αwill␈αcompute␈αa␈αcheck␈αsum␈αof␈αitself␈αevery␈αfew␈αminutes␈αto␈αverify␈αthat␈αit␈αhasn't␈αbeen␈αchanged
␈↓ α∧␈↓by a software or hardware malfunction.

␈↓ α∧␈↓␈↓ αTIn␈α⊂principle,␈α⊂introspection␈α⊂is␈α⊂easier␈α⊂for␈α⊂computer␈α⊂programs␈α⊂than␈α⊂for␈α⊂people,␈α⊂because␈α⊂the
␈↓ α∧␈↓entire␈α⊂memory␈α⊂in␈α⊂which␈α⊂programs␈α⊂and␈α⊂data␈α⊃are␈α⊂stored␈α⊂is␈α⊂available␈α⊂for␈α⊂inspection.␈α⊂ In␈α⊃fact,␈α⊂a
␈↓ α∧␈↓computer␈αprogram␈αcan␈αbe␈αmade␈αto␈αpredict␈αhow␈αit␈αwould␈αreact␈αto␈αparticular␈αinputs␈αprovided␈αit␈α
has
␈↓ α∧␈↓enough␈α
free␈α
storage␈α
to␈αperform␈α
the␈α
calculation.␈α
 This␈α
situation␈αsmells␈α
of␈α
paradox,␈α
and␈α
there␈αis␈α
one.
␈↓ α∧␈↓Namely,␈α∂if␈α∂a␈α∂program␈α∂could␈α∂predict␈α∂its␈α∂own␈α∂actions␈α∞in␈α∂less␈α∂time␈α∂than␈α∂it␈α∂takes␈α∂to␈α∂carry␈α∂out␈α∞the
␈↓ α∧␈↓action,␈αit␈αcould␈αrefuse␈αto␈αdo␈αwhat␈αit␈αhas␈αpredicted␈αfor␈αitself.␈α This␈αonly␈αshows␈αthat␈αself-simulation
␈↓ α∧␈↓is necessarily a slow process, and this is not surprising.

␈↓ α∧␈↓␈↓ αTHowever,␈α
present␈α
programs␈α
do␈α
little␈α
interesting␈α
introspection.␈α
 This␈α
is␈α
just␈α
a␈α
matter␈α∞of␈α
the
␈↓ α∧␈↓undeveloped␈αstate␈αof␈αartificial␈αintelligence;␈αprogrammers␈αdon't␈αyet␈αknow␈αhow␈αto␈αmake␈αa␈αcomputer
␈↓ α∧␈↓program look at itself in a useful way.

␈↓ α∧␈↓␈↓ αT3.␈α∃ ␈↓αConsciousness␈α∃and␈α⊗self-consciousness␈↓.␈α∃ Suppose␈α∃we␈α⊗wish␈α∃to␈α∃distinguish␈α⊗the␈α∃self-
␈↓ α∧␈↓awareness␈α⊃of␈α⊂a␈α⊃machine,␈α⊃animal␈α⊂or␈α⊃person␈α⊃from␈α⊂its␈α⊃awareness␈α⊃of␈α⊂other␈α⊃things.␈α⊃ We␈α⊂explicate
␈↓ α∧␈↓awareness␈αas␈αbelief␈αin␈αcertain␈αsentences,␈αso␈αin␈αthis␈αcase␈αwe␈αare␈αwant␈αto␈αdistinguish␈αthose␈αsentences
␈↓ α∧␈↓or␈αthose␈αterms␈αin␈αthe␈αsentences␈αthat␈αmay␈αbe␈αconsidered␈αto␈αbe␈αabout␈αthe␈αself.␈α We␈αalso␈αdon't␈αexpect
␈↓ α∧␈↓that␈α∂self-consciousness␈α∞will␈α∂be␈α∞a␈α∂single␈α∞property␈α∂that␈α∞something␈α∂either␈α∞has␈α∂or␈α∞hasn't␈α∂but␈α∞rather
␈↓ α∧␈↓there␈α∂will␈α∂be␈α∂many␈α∂kinds␈α∂of␈α∂self-awareness␈α∂with␈α∂humans␈α∂posessing␈α∂many␈α∂of␈α∂the␈α∂kinds␈α⊂we␈α∂can
␈↓ α∧␈↓imagine.

␈↓ α∧␈↓␈↓ αTHere are some of the kinds of self-awareness:

␈↓ α∧␈↓␈↓ β$3.1.␈α∂Certain␈α⊂predicates␈α∂of␈α∂the␈α⊂situation␈α∂(propositional␈α∂fluents␈α⊂in␈α∂the␈α⊂terminology␈α∂of
␈↓ α∧␈↓(McCarthy␈α∂and␈α∞Hayes␈α∂1969))␈α∂are␈α∞directly␈α∂observable␈α∞in␈α∂almost␈α∂all␈α∞situations␈α∂while␈α∂others␈α∞often
␈↓ α∧␈↓must␈α∞be␈α∞inferred.␈α∞ The␈α∞almost␈α∞always␈α∂observable␈α∞fluents␈α∞may␈α∞reasonably␈α∞be␈α∞identified␈α∂with␈α∞the
␈↓ α∧␈↓senses.␈α
 Likewise␈α
the␈α
values␈α
of␈α
certain␈α
fluents␈α
are␈α
almost␈α
always␈α
under␈α
the␈α
control␈α
of␈α
the␈α
being␈α
and


␈↓ α∧␈↓␈↓ εu16␈↓ ∧



␈↓ α∧␈↓can␈α⊂be␈α⊂called␈α∂motor␈α⊂parameters␈α⊂for␈α∂lack␈α⊂of␈α⊂a␈α∂common␈α⊂language␈α⊂term.␈α∂ We␈α⊂have␈α⊂in␈α⊂mind␈α∂the
␈↓ α∧␈↓positions␈α∩of␈α∩the␈α∩joints.␈α∩ Most␈α∩motor␈α⊃parameters␈α∩are␈α∩both␈α∩observable␈α∩and␈α∩controllable.␈α∩ I␈α⊃am
␈↓ α∧␈↓inclined␈αto␈α
regard␈αthe␈α
posession␈αof␈α
a␈αsubstantial␈αset␈α
of␈αsuch␈α
constantly␈αobservable␈α
or␈αcontrollable
␈↓ α∧␈↓fluents␈α
as␈αthe␈α
most␈αprimitive␈α
form␈α
of␈αself-consciousness,␈α
but␈αI␈α
have␈αno␈α
strong␈α
arguments␈αagainst
␈↓ α∧␈↓someone who wished to require more.

␈↓ α∧␈↓␈↓ β$3.2.␈αThe␈αsecond␈αlevel␈αof␈αself-consciousness␈αrequires␈αa␈αterm␈α␈↓↓I␈↓␈αin␈αthe␈αlanguage␈αdenoting
␈↓ α∧␈↓the␈αself.␈α ␈↓↓I␈↓␈αshould␈αbelong␈αto␈αthe␈αclass␈αof␈αpersistent␈αobjects␈αand␈αsome␈αof␈αthe␈αsame␈αpredicates␈αshould
␈↓ α∧␈↓be␈α∂applicable␈α∂to␈α∂it␈α∂as␈α∂are␈α∂applicable␈α∂to␈α∂other␈α∂objects.␈α∂ For␈α∂example,␈α∂like␈α∂other␈α∂objects␈α∂␈↓↓I␈↓␈α∂has␈α∂a
␈↓ α∧␈↓location␈αthat␈αcan␈αchange␈αin␈αtime.␈α ␈↓↓I␈↓␈αis␈αalso␈αvisible␈αand␈αimpenetrable␈αlike␈αother␈αobjects.␈α However,
␈↓ α∧␈↓we␈αdon't␈αwant␈αto␈αget␈αcarried␈αaway␈αin␈αregarding␈αa␈αphysical␈αbody␈αas␈αa␈αnecessary␈αcondition␈αfor␈αself-
␈↓ α∧␈↓consciousness.␈α Imagine␈α
a␈αdistributed␈α
computer␈αwhose␈α
sense␈αand␈αmotor␈α
organs␈αcould␈α
also␈αbe␈α
in␈αa
␈↓ α∧␈↓variety of places.  We don't want to exclude it from self-consciousness by definition.

␈↓ α∧␈↓␈↓ β$3.3.␈α∪The␈α∪third␈α∪level␈α∪come␈α∪when␈α∪␈↓↓I␈↓␈α∪is␈α∪regarded␈α∪as␈α∪an␈α∪actor␈α∪among␈α∪others.␈α∪ The
␈↓ α∧␈↓conditions␈αthat␈αpermit␈α␈↓↓I␈↓␈αto␈αdo␈αsomething␈αare␈αsimilar␈αto␈αthe␈αconditions␈αthat␈αpermit␈αother␈αactors␈αto
␈↓ α∧␈↓do similar things.

␈↓ α∧␈↓␈↓ β$3.4.␈α
The␈α
fourth␈α∞level␈α
requires␈α
the␈α
applicability␈α∞of␈α
predicates␈α
such␈α
as␈α∞␈↓↓believes,␈↓␈α
␈↓↓wants␈↓
␈↓ α∧␈↓and␈α␈↓↓can␈↓␈αto␈α
␈↓↓I.␈↓␈αBeliefs␈αabout␈α
past␈αsituations␈αand␈α
the␈αability␈αto␈α
hypothesize␈αfuture␈αsituations␈αare␈α
also
␈↓ α∧␈↓required for this level.

␈↓ α∧␈↓␈↓ αT4.␈α⊗␈↓αLanguage␈α⊗and␈α⊗thought␈↓.␈α⊗ Here␈α⊗is␈α⊗a␈α⊗hypothesis␈α⊗arising␈α⊗from␈α↔artificial␈α⊗intelligence
␈↓ α∧␈↓concerning␈α∪the␈α∪relation␈α∪between␈α∪language␈α∪and␈α∪thought.␈α∪ Imagine␈α∪a␈α∪person␈α∪or␈α∀machine␈α∪that
␈↓ α∧␈↓represents␈αinformation␈αinternally␈αin␈αa␈αhuge␈αnetwork.␈α Each␈αnode␈αof␈αthe␈αnetwork␈αhas␈αreferences␈αto
␈↓ α∧␈↓other␈α⊃nodes␈α⊃through␈α⊃relations.␈α⊃ (If␈α⊃the␈α⊃system␈α⊃has␈α⊃a␈α⊃variable␈α⊃collection␈α⊃of␈α⊃relations,␈α⊃then␈α⊂the
␈↓ α∧␈↓relations␈α∞have␈α∞to␈α∞be␈α∞represented␈α∞by␈α∞nodes,␈α∞and␈α∞we␈α∞get␈α∞a␈α∞symmetrical␈α∞theory␈α∞if␈α∞we␈α∞suppose␈α∞that
␈↓ α∧␈↓each␈αnode␈αis␈αconnected␈αto␈αa␈αset␈αof␈αpairs␈αof␈αother␈αnodes).␈α We␈αcan␈αimagine␈αthis␈αstructure␈αto␈αhave␈αa
␈↓ α∧␈↓long␈αterm␈αpart␈αand␈αalso␈αextremely␈αtemporary␈αparts␈αrepresenting␈αcurrent␈α␈↓↓thoughts␈↓.␈α Naturally,␈αeach
␈↓ α∧␈↓being␈α∞has␈α∞a␈α∞its␈α∞own␈α∞network␈α∞depending␈α∂on␈α∞its␈α∞own␈α∞experience.␈α∞A␈α∞thought␈α∞is␈α∞then␈α∂a␈α∞temporary
␈↓ α∧␈↓node␈αcurrently␈α
being␈αreferenced␈α
by␈αthe␈α
mechanism␈αof␈α
consciousness.␈α Its␈α
meaning␈αis␈αdetermined␈α
by
␈↓ α∧␈↓its␈αreferences␈αto␈αother␈αnodes␈αwhich␈αin␈αturn␈αrefer␈αto␈αyet␈αother␈αnodes.␈α Now␈αconsider␈αthe␈αproblem␈α
of
␈↓ α∧␈↓communicating a thought to another being.

␈↓ α∧␈↓␈↓ αTIts␈α
full␈α
communication␈α∞would␈α
involve␈α
transmitting␈α
the␈α∞entire␈α
network␈α
that␈α
can␈α∞be␈α
reached
␈↓ α∧␈↓from␈α⊂the␈α⊂given␈α⊂node,␈α⊂and␈α⊂this␈α⊂would␈α⊂ordinarily␈α⊂constitute␈α⊂the␈α⊂entire␈α⊂experience␈α⊂of␈α⊂the␈α⊂being.
␈↓ α∧␈↓More␈αthan␈αthat,␈αit␈αwould␈αbe␈αnecessary␈αto␈αalso␈αcommunicate␈αthe␈αprograms␈αthat␈αthat␈αtake␈αaction␈αon
␈↓ α∧␈↓the␈αbasis␈αof␈αencountering␈αcertain␈αnodes.␈α Even␈αif␈αall␈αthis␈αcould␈αbe␈αtransmitted,␈αthe␈αrecipient␈αwould
␈↓ α∧␈↓still␈α∪have␈α∩to␈α∪find␈α∩equivalents␈α∪for␈α∩the␈α∪information␈α∩in␈α∪terms␈α∩of␈α∪its␈α∩own␈α∪network.␈α∩ Therefore,
␈↓ α∧␈↓thoughts have to be translated into a public language before they can be commuunicated.

␈↓ α∧␈↓␈↓ αTA␈αlanguage␈αis␈αalso␈αa␈αnetwork␈αof␈αassociations␈αand␈αprograms.␈α However,␈αcertain␈αof␈αthe␈αnodes
␈↓ α∧␈↓in␈α∂this␈α∂network␈α∞(more␈α∂accurately␈α∂a␈α∞␈↓↓family␈↓␈α∂of␈α∂networks,␈α∞since␈α∂no␈α∂two␈α∞people␈α∂speak␈α∂precisely␈α∞the
␈↓ α∧␈↓same␈α
language)␈α
are␈αassociated␈α
with␈α
words␈αor␈α
set␈α
phrases.␈α Sometimes␈α
the␈α
translation␈αfrom␈α
thoughts
␈↓ α∧␈↓to␈α
sentences␈α
is␈α
easy,␈α
because␈αlarge␈α
parts␈α
of␈α
the␈α
private␈αnetworks␈α
are␈α
taken␈α
from␈α
the␈αpublic␈α
network,
␈↓ α∧␈↓and␈α
there␈αis␈α
an␈α
advantage␈αin␈α
preserving␈αthe␈α
correspondence.␈α
 However,␈αthe␈α
translation␈α
is␈αalways
␈↓ α∧␈↓approximate␈α∂(in␈α∂sense␈α∂that␈α∂still␈α∂lacks␈α∂a␈α∂technical␈α∂definition),␈α∂and␈α∂some␈α∂areas␈α∂of␈α∂experience␈α∂are


␈↓ α∧␈↓␈↓ εu17␈↓ ∧



␈↓ α∧␈↓difficult␈α∪to␈α∀translate␈α∪at␈α∪all.␈α∀ Sometimes␈α∪this␈α∀is␈α∪for␈α∪intrinsic␈α∀reasons,␈α∪and␈α∀sometimes␈α∪because
␈↓ α∧␈↓particular␈αcultures␈αdon't␈αuse␈αlanguage␈αin␈αthis␈αarea.␈α (It␈αis␈αmy␈αimpression␈αthat␈αcultures␈αdiffer␈αin␈αthe
␈↓ α∧␈↓extent␈αto␈αwhich␈αinformation␈αabout␈αfacial␈α
appearance␈αthat␈αcan␈αbe␈αused␈αfor␈αrecognition␈α
is␈αverbally
␈↓ α∧␈↓transmitted).␈α According␈αto␈αthis␈αscheme,␈αthe␈α"deep␈αstructure"␈αof␈αa␈αpublicly␈αexpressible␈αthought␈αis␈αa
␈↓ α∧␈↓node␈αin␈αthe␈αpublic␈αnetwork.␈α It␈αis␈αtranslated␈αinto␈αthe␈αdeep␈αstructure␈αof␈αa␈αsentence␈αas␈αa␈αtree␈αwhose
␈↓ α∧␈↓terminal␈α
nodes␈α
are␈α
the␈α
nodes␈α
to␈α
which␈αwords␈α
or␈α
set␈α
phrases␈α
are␈α
attached.␈α
 This␈α
"deep␈αstructure"
␈↓ α∧␈↓then must be translated into a string in a spoken or written language.

␈↓ α∧␈↓␈↓ αTThe␈α
need␈αto␈α
use␈αlanguage␈α
to␈αexpress␈α
thought␈αalso␈α
applies␈αwhen␈α
we␈αhave␈α
to␈αascribe␈α
thoughts
␈↓ α∧␈↓to other beings, since we cannot put the entire network into a single sentence.

␈↓ α∧␈↓␈↓ αT5.␈α␈↓αIntentions␈↓.␈α We␈αare␈αtempted␈αto␈αsay␈αthat␈αa␈αmachine␈α␈↓↓intends␈↓␈αto␈αperform␈αan␈αaction␈αwhen␈αit
␈↓ α∧␈↓believes␈α∀it␈α∀will␈α∪and␈α∀also␈α∀believes␈α∪that␈α∀it␈α∀could␈α∪do␈α∀otherwise.␈α∀ However,␈α∪we␈α∀will␈α∀resist␈α∪this
␈↓ α∧␈↓temptation␈αand␈αpropose␈αthat␈αa␈αpredicate␈α␈↓↓intends(actor,action,state)␈↓␈αbe␈αsuitably␈αaxiomatized␈αwhere
␈↓ α∧␈↓one␈αof␈αthe␈αaxioms␈αsay␈αthat␈αthe␈αmachine␈αintends␈αthe␈αaction␈αif␈αit␈αbelieves␈αit␈αwill␈αperform␈αthe␈αaction
␈↓ α∧␈↓and␈α∞could␈α∞do␈α∞otherwise.␈α∞ Armstrong␈α∞(1968)␈α
wants␈α∞to␈α∞require␈α∞an␈α∞element␈α∞of␈α∞servo-mechanism␈α
in
␈↓ α∧␈↓order␈αthat␈αa␈αbelief␈αthat␈αan␈αaction␈αwill␈αbe␈αperformed␈αbe␈αregarded␈αas␈αan␈αintention,␈αi.e.␈αthere␈αshould
␈↓ α∧␈↓be␈α⊂a␈α⊂commitment␈α⊂to␈α⊂do␈α⊂it␈α⊂one␈α⊂way␈α∂or␈α⊂another.␈α⊂ There␈α⊂may␈α⊂be␈α⊂good␈α⊂reasons␈α⊂to␈α⊂allow␈α∂several
␈↓ α∧␈↓versions of intention to co-exist in the same formalism.

␈↓ α∧␈↓␈↓ αT6.␈α␈↓αFree␈αwill␈↓.␈α When␈αwe␈αprogram␈αa␈αcomputer␈αto␈αmake␈αchoices␈αintelligently␈αafter␈αdetermining
␈↓ α∧␈↓its␈αoptions,␈αexamining␈αtheir␈αconsequences,␈αand␈αdeciding␈αwhich␈αis␈αmost␈αfavorable␈αor␈αmost␈αmoral␈αor
␈↓ α∧␈↓whatever,␈α∪we␈α∩must␈α∪program␈α∩it␈α∪to␈α∩take␈α∪an␈α∩attitude␈α∪towards␈α∩its␈α∪freedom␈α∩of␈α∪choice␈α∩essentially
␈↓ α∧␈↓isomorphic␈αto␈α
that␈αwhich␈α
a␈αhuman␈α
must␈αtake␈α
to␈αhis␈αown.␈α
 A␈αprogram␈α
will␈αhave␈α
to␈αtake␈α
such␈αan
␈↓ α∧␈↓attitude towards another unless it knows the details of the other's construction and present state.

␈↓ α∧␈↓␈↓ αTWe␈α⊃can␈α⊃define␈α⊂whether␈α⊃a␈α⊃particular␈α⊃action␈α⊂was␈α⊃free␈α⊃or␈α⊃forced␈α⊂␈↓↓relative␈α⊃to␈α⊃a␈α⊃theory␈↓␈α⊂that
␈↓ α∧␈↓ascribes␈αbeliefs␈αand␈αwithin␈αwhich␈α
beings␈αdo␈αwhat␈αthey␈αbelieve␈α
will␈αadvance␈αtheir␈αgoals.␈α In␈αsuch␈α
a
␈↓ α∧␈↓theory,␈α∞action␈α∞is␈α∞precipitated␈α∞by␈α∞a␈α∞belief␈α∞of␈α∞the␈α∂form␈α∞␈↓↓I␈α∞should␈α∞do␈α∞X␈α∞now␈↓.␈α∞ We␈α∞will␈α∞say␈α∂that␈α∞the
␈↓ α∧␈↓action␈αwas␈αfree␈αif␈α
changing␈αthe␈αbelief␈αto␈α
␈↓↓I␈αshouldn't␈αdo␈αX␈αnow␈↓␈α
would␈αhave␈αresulted␈αin␈α
the␈αaction
␈↓ α∧␈↓not␈α∞being␈α∞performed.␈α∞ This␈α∞requires␈α∞that␈α
the␈α∞theory␈α∞of␈α∞belief␈α∞have␈α∞sufficient␈α∞Cartesian␈α
product
␈↓ α∧␈↓structure␈αso␈αthat␈αchanging␈αa␈αsingle␈αbelief␈αis␈αdefined,␈αbut␈αit␈αdoesn't␈αrequire␈αdefining␈αwhat␈αthe␈αstate
␈↓ α∧␈↓of the world would be if a single belief were different.

␈↓ α∧␈↓␈↓ αTIt␈α⊃may␈α⊃be␈α⊃possible␈α⊃to␈α⊃separate␈α⊃the␈α⊃notion␈α⊂of␈α⊃a␈α⊃␈↓↓free␈α⊃action␈↓␈α⊃into␈α⊃a␈α⊃technical␈α⊃part␈α⊃and␈α⊂a
␈↓ α∧␈↓controversial␈α⊃part.␈α⊃ The␈α∩technical␈α⊃part␈α⊃would␈α⊃define␈α∩freedom␈α⊃relative␈α⊃to␈α⊃an␈α∩approximate␈α⊃co-
␈↓ α∧␈↓ordinate␈α~system␈α≠giving␈α~the␈α~necessary␈α≠Cartesian␈α~product␈α~structure.␈α≠ Relative␈α~to␈α≠the␈α~co-
␈↓ α∧␈↓ordinatization,␈α∂the␈α∂freedom␈α∞of␈α∂a␈α∂particular␈α∂action␈α∞would␈α∂be␈α∂a␈α∞technical␈α∂issue,␈α∂but␈α∂people␈α∞could
␈↓ α∧␈↓argue about whether to accept the whole co-ordinate system.

␈↓ α∧␈↓␈↓ αTThis␈α
isn't␈α
the␈α
whole␈αfree␈α
will␈α
story,␈α
because␈α
moralists␈αare␈α
also␈α
concerned␈α
with␈αwhether␈α
praise
␈↓ α∧␈↓or␈αblame␈αmay␈αbe␈αattributed␈α
to␈αa␈αchoice.␈α The␈αfollowing␈α
considerations␈αwould␈αseem␈αto␈αapply␈αto␈α
any
␈↓ α∧␈↓attempt to define the morality of actions in a way that would apply to machines:

␈↓ α∧␈↓␈↓ β$6.1.␈αThere␈αis␈αunlikely␈αto␈αbe␈αa␈αsimple␈αbehavioral␈αdefinition.␈α Instead␈αthere␈αwould␈αbe␈αa
␈↓ α∧␈↓second order definition criticizing predicates that ascribe morality to actions.



␈↓ α∧␈↓␈↓ εu18␈↓ ∧



␈↓ α∧␈↓␈↓ β$6.2.␈α∩The␈α∪theory␈α∩must␈α∪contain␈α∩at␈α∩least␈α∪one␈α∩axiom␈α∪of␈α∩morality␈α∩that␈α∪is␈α∩not␈α∪just␈α∩a
␈↓ α∧␈↓statement of physical fact.  Relative to this axiom, moral judgments of actions can be factual.

␈↓ α∧␈↓␈↓ β$6.3.␈αThe␈αtheory␈αof␈αmorality␈αwill␈αpresuppose␈αa␈αtheory␈αof␈αbelief␈αin␈αwhich␈αstatements␈αof
␈↓ α∧␈↓the␈αform␈α␈↓↓"It␈αbelieved␈αthe␈αaction␈αwould␈αharm␈αsomeone"␈↓␈αare␈αdefined.␈α The␈αtheory␈αmust␈αascribe␈αbeliefs
␈↓ α∧␈↓about others' welfare and perhaps about the being's own welfare.

␈↓ α∧␈↓␈↓ β$6.4.␈α⊂It␈α⊃might␈α⊂be␈α⊃necessary␈α⊂to␈α⊃consider␈α⊂the␈α⊂machine␈α⊃as␈α⊂imbedded␈α⊃in␈α⊂some␈α⊃kind␈α⊂of
␈↓ α∧␈↓society in order to ascribe morality to its actions.

␈↓ α∧␈↓␈↓ β$6.5.␈αNo␈αpresent␈αmachines␈αadmit␈αsuch␈αa␈αbelief␈αstructure,␈αand␈αno␈αsuch␈αstructure␈αmay␈αbe
␈↓ α∧␈↓required␈α∂to␈α∂make␈α∂a␈α∂machine␈α∂with␈α∂arbitrarily␈α∂high␈α∂intelligence␈α∂in␈α∂the␈α∂sense␈α∂of␈α∞problem-solving
␈↓ α∧␈↓ability.

␈↓ α∧␈↓␈↓ β$6.6.␈α∂It␈α∂seems␈α⊂unlikely␈α∂that␈α∂morally␈α∂judgable␈α⊂machines␈α∂or␈α∂machines␈α∂to␈α⊂which␈α∂rights
␈↓ α∧␈↓might legitimately be ascribed should be made if and when it becomes possible to do so.

































␈↓ α∧␈↓␈↓ εu19␈↓ ∧



␈↓ α∧␈↓α␈↓ ¬(OTHER VIEWS ABOUT MIND

␈↓ α∧␈↓␈↓ αT␈↓↓Caveat:␈α∞The␈α
present␈α∞version␈α∞of␈α
this␈α∞section␈α∞is␈α
not␈α∞very␈α∞successful␈α
in␈α∞describing␈α∞the␈α
relations
␈↓ α∧␈↓↓between␈αthese␈αviews␈αand␈αothers␈αin␈αthe␈αliterature.␈α
 While␈αcriticism␈αof␈αthis␈αsection␈αwill␈αbe␈αmost␈α
helpful
␈↓ α∧␈↓↓in improving it, it is not the main part of this paper␈↓.

␈↓ α∧␈↓␈↓ αTThe␈α∞fundamental␈α∞difference␈α∞in␈α∞point␈α∞of␈α∞view␈α∞between␈α∞this␈α∞paper␈α∞and␈α∞most␈α∞philosophy␈α∞is
␈↓ α∧␈↓that␈α⊃we␈α⊃are␈α⊃motivated␈α⊃by␈α⊃the␈α⊃problem␈α⊃of␈α⊃designing␈α⊃an␈α⊃artificial␈α⊃intelligence.␈α⊃ Therefore,␈α⊃our
␈↓ α∧␈↓attitude␈α
towards␈α
a␈α
concept␈α
like␈α
␈↓↓belief␈↓␈α
is␈αdetermined␈α
by␈α
trying␈α
to␈α
decide␈α
what␈α
ways␈α
of␈αacquiring␈α
and
␈↓ α∧␈↓using␈α
beliefs␈αwill␈α
lead␈αto␈α
intelligent␈αbehavior.␈α
 Then␈αwe␈α
discover␈αthat␈α
much␈αthat␈α
one␈αintelligence
␈↓ α∧␈↓can find out about another can be expressed by ascribing beliefs to it.

␈↓ α∧␈↓␈↓ αTA␈α
negative␈α
view␈α
of␈α
empiricism␈α
seems␈α
dictated␈α
from␈α
the␈α
apparent␈α
artificiality␈α
of␈α
designing␈α
an
␈↓ α∧␈↓empiricist␈α
computer␈α
program.␈α
 Namely,␈α
we␈α
plan␈α
to␈α
provide␈α
our␈α
program␈α
with␈α
certain␈α
senses,␈αbut
␈↓ α∧␈↓we␈αhave␈αno␈αway␈αof␈αensuring␈αthat␈αthe␈αworld␈αin␈αwhich␈αwe␈αare␈αputting␈αthe␈αmachine␈αis␈αconstructable
␈↓ α∧␈↓from␈αthe␈αsense␈αimpressions␈αit␈αwill␈αhave.␈α Whether␈αit␈αwill␈αever␈αknow␈αsome␈αfact␈αabout␈αthe␈αworld␈αis
␈↓ α∧␈↓contingent,␈αso␈αwe␈αare␈αnot␈αinclined␈α
to␈αbuild␈αinto␈αit␈αthe␈αnotion␈α
that␈αwhat␈αit␈αcan't␈αknow␈αabout␈α
doesn't
␈↓ α∧␈↓exist.

␈↓ α∧␈↓␈↓ αTThe␈αphilosophical␈α
views␈αmost␈αsympathetic␈α
to␈αour␈αapproach␈α
are␈αsome␈αexpressed␈α
by␈αCarnap
␈↓ α∧␈↓in some of the discursive sections of (Carnap 1956).

␈↓ α∧␈↓␈↓ αTPutnam␈α(1961)␈αmay␈αhave␈αbeen␈αthe␈αfirst␈αto␈αargue␈αthat␈αthe␈αclassical␈αmind-body␈αproblems␈αare
␈↓ α∧␈↓just␈αas␈αacute␈α
for␈αmachines␈αas␈α
for␈αmen.␈α Some␈αof␈α
his␈αarguments␈αare␈α
more␈αexplicit␈αthan␈α
any␈αgiven
␈↓ α∧␈↓here, but in that paper, he doesn't try to solve the problems for machines.

␈↓ α∧␈↓␈↓ αTD.M.␈α∞Armstrong␈α∞(1968)␈α
␈↓↓"attempts␈α∞to␈α∞show␈α
that␈α∞there␈α∞are␈α
no␈α∞valid␈α∞philososophical␈α∞or␈α
logical
␈↓ α∧␈↓↓reasons␈α
for␈α
rejecting␈α
the␈α
identification␈α
of␈α
mind␈α
and␈α
brain."␈↓␈α
He␈α
does␈α
this␈α
by␈α
proposing␈αdefinitions␈α
of
␈↓ α∧␈↓mental␈α
concepts␈α∞in␈α
terms␈α∞of␈α
the␈α∞state␈α
of␈α
the␈α∞brain.␈α
 Fundamentally,␈α∞I␈α
agree␈α∞with␈α
him␈α∞and␈α
think
␈↓ α∧␈↓that␈α∞such␈α∞a␈α∞program␈α∞of␈α∂definition␈α∞can␈α∞be␈α∞carried␈α∞out,␈α∞but␈α∂it␈α∞seems␈α∞to␈α∞me␈α∞that␈α∞his␈α∂methods␈α∞for
␈↓ α∧␈↓defining␈α∞mental␈α
qualities␈α∞as␈α∞brain␈α
states␈α∞are␈α∞too␈α
weak␈α∞even␈α∞for␈α
defining␈α∞properties␈α∞of␈α
computer
␈↓ α∧␈↓programs.  While he goes beyond behavioral definitions as such, he relies on dispositional states.

␈↓ α∧␈↓␈↓ αTThis␈αpaper␈αis␈αpartly␈αan␈αattempt␈αto␈αdo␈αwhat␈αRyle␈α(1949)␈αsays␈αcan't␈αbe␈αdone␈αand␈αshouldn't␈αbe
␈↓ α∧␈↓attempted␈α∞-␈α∞namely␈α∞to␈α∞define␈α∂mental␈α∞qualities␈α∞in␈α∞terms␈α∞of␈α∂states␈α∞of␈α∞a␈α∞machine.␈α∞ The␈α∂attempt␈α∞is
␈↓ α∧␈↓based␈α
on␈α
methods␈α
of␈α
which␈α
he␈α∞would␈α
not␈α
approve;␈α
he␈α
implicitly␈α
requires␈α
first␈α∞order␈α
definitions,
␈↓ α∧␈↓and␈αhe␈αimplicitly␈αrequires␈αthat␈αdefinitions␈αbe␈αmade␈αin␈αterms␈αof␈αthe␈αstate␈αof␈αthe␈αworld␈αand␈α
not␈αin
␈↓ α∧␈↓terms of approximate theories.

␈↓ α∧␈↓␈↓ αTHis␈α∃final␈α∃view␈α∃of␈α∀the␈α∃proper␈α∃subject␈α∃matter␈α∃of␈α∀epistemology␈α∃is␈α∃too␈α∃narrow␈α∃to␈α∀help
␈↓ α∧␈↓researchers␈α∂in␈α∂artificial␈α∂intelligence.␈α∞ Namely,␈α∂we␈α∂need␈α∂help␈α∞in␈α∂expressing␈α∂those␈α∂facts␈α∂about␈α∞the
␈↓ α∧␈↓world␈αthat␈αcan␈αbe␈αobtained␈αin␈αan␈αordinary␈αsituation␈αby␈αan␈αordinary␈αperson␈αand␈αthe␈αgeneral␈αfacts
␈↓ α∧␈↓about␈αthe␈αworld␈αwill␈αenable␈αour␈αprogram␈αto␈αdecide␈αto␈αcall␈αa␈αtravel␈αagent␈αto␈αfind␈αout␈αhow␈αto␈αget␈αto
␈↓ α∧␈↓Boston.

␈↓ α∧␈↓␈↓ αTDonald␈α∃Davidson␈α∀(1973)␈α∃undertakes␈α∀to␈α∃show,␈α∀␈↓↓"There␈α∃is␈α∀no␈α∃important␈α∀sense␈α∃in␈α∀which
␈↓ α∧␈↓↓psychology␈α⊃can␈α∩be␈α⊃reduced␈α⊃to␈α∩the␈α⊃physical␈α⊃sciences"␈↓.␈α∩ He␈α⊃proceeds␈α⊃by␈α∩arguing␈α⊃that␈α∩the␈α⊃mental


␈↓ α∧␈↓␈↓ εu20␈↓ ∧



␈↓ α∧␈↓qualities␈α∂of␈α∂a␈α∂hypothetical␈α∂artificial␈α∂man␈α∂could␈α∂not␈α∂be␈α∂defined␈α∂physically␈α∂even␈α∂if␈α∂we␈α∂knew␈α∂the
␈↓ α∧␈↓details of its physical structure.

␈↓ α∧␈↓␈↓ αTOne␈α∂sense␈α∂of␈α∂Davidson's␈α⊂statement␈α∂does␈α∂not␈α∂require␈α⊂the␈α∂arguments␈α∂he␈α∂gives.␈α⊂ There␈α∂are
␈↓ α∧␈↓many␈α∂universal␈α∞computing␈α∂elements␈α∂-␈α∞relays,␈α∂neurons,␈α∞gates␈α∂and␈α∂flip-flops,␈α∞and␈α∂physics␈α∂tells␈α∞us
␈↓ α∧␈↓many␈α
ways␈α
of␈α
constructing␈α
them.␈α
 Any␈α∞information␈α
processing␈α
system␈α
that␈α
can␈α
be␈α∞constructed␈α
of
␈↓ α∧␈↓one␈α
kind␈α∞of␈α
element␈α∞can␈α
be␈α∞constructed␈α
of␈α∞any␈α
other.␈α∞ Therefore,␈α
physics␈α∞tells␈α
us␈α∞nothing␈α
about
␈↓ α∧␈↓what␈α
information␈α∞processes␈α
exist␈α∞in␈α
nature␈α∞or␈α
can␈α
be␈α∞constructed.␈α
 Computer␈α∞science␈α
is␈α∞no␈α
more
␈↓ α∧␈↓reducible to physics than is psychology.

␈↓ α∧␈↓␈↓ αTHowever,␈αDavidson␈αalso␈α
argues␈αthat␈αthe␈αmental␈α
states␈αof␈αan␈α
organism␈αare␈αnot␈αdescribable␈α
in
␈↓ α∧␈↓terms␈αof␈αits␈αphysical␈αstructure,␈αand␈αI␈αtake␈αthis␈αto␈αassert␈αalso␈αthat␈αthey␈αare␈αnot␈αdescribable␈αin␈αterms
␈↓ α∧␈↓of␈αits␈αconstruction␈αfrom␈αlogical␈αelements.␈α
 His␈αarguments␈αtend␈αto␈αshow␈αthat␈αmental␈α
qualities␈αdon't
␈↓ α∧␈↓have␈α∂what␈α∂I␈α∂have␈α∂called␈α∂first␈α∂order␈α∂structural␈α∂definitions.␈α∂ It␈α∂isn't␈α∂obvious␈α∂what␈α∂he␈α⊂would␈α∂say
␈↓ α∧␈↓about second order definitions.


































␈↓ α∧␈↓␈↓ εu21␈↓ ∧



␈↓ α∧␈↓α␈↓ αTNOTES

␈↓ α∧␈↓␈↓ αT1.␈α∪(McCarthy␈α∪and␈α∪Hayes␈α∀1969)␈α∪defines␈α∪an␈α∪␈↓↓epistemologically␈α∪adequate␈↓␈α∀representation␈α∪of
␈↓ α∧␈↓information␈α
as␈α
one␈α
that␈α
can␈α
express␈α
the␈α
information␈α
actually␈α
available␈α
to␈α
a␈α
subject␈α∞under␈α
given
␈↓ α∧␈↓circumstances.␈α Thus␈α
when␈αwe␈αsee␈α
a␈αperson,␈αparts␈α
of␈αhim␈αare␈α
occluded,␈αand␈αwe␈α
use␈αour␈αmemory␈α
of
␈↓ α∧␈↓previous␈αlooks␈αat␈αhim␈αand␈αour␈αgeneral␈αknowledge␈αof␈αhumans␈αto␈αfinish␈αof␈αa␈α"picture"␈αof␈αhim␈αthat
␈↓ α∧␈↓includes␈α⊃both␈α⊃two␈α∩and␈α⊃three␈α⊃dimensional␈α⊃information.␈α∩ We␈α⊃must␈α⊃also␈α∩consider␈α⊃␈↓↓metaphysically
␈↓ α∧␈↓↓adequate␈↓␈αrepresentations␈αthat␈αcan␈αrepresent␈αcomplete␈αfacts␈αignoring␈αthe␈αsubject's␈αability␈αto␈αacquire
␈↓ α∧␈↓the␈α∞facts␈α
in␈α∞given␈α
circumstances.␈α∞ Thus␈α∞Laplace␈α
thought␈α∞that␈α
the␈α∞positions␈α
and␈α∞velocities␈α∞of␈α
the
␈↓ α∧␈↓particles␈αgave␈αa␈αmetaphysically␈αadequate␈αrepresentation.␈α Metaphysically␈α
adequate␈αrepresentations
␈↓ α∧␈↓are␈α⊂needed␈α∂for␈α⊂scientific␈α⊂and␈α∂other␈α⊂theories,␈α∂but␈α⊂artificial␈α⊂intelligence␈α∂and␈α⊂a␈α⊂full␈α∂philosophical
␈↓ α∧␈↓treatment␈α⊃of␈α⊃common␈α⊃sense␈α⊃experience␈α⊃also␈α⊃require␈α⊃epistemologically␈α⊃adequate␈α⊃representations.
␈↓ α∧␈↓This␈α∃paper␈α∃might␈α∃be␈α∃summarized␈α∃as␈α⊗contending␈α∃that␈α∃mental␈α∃concepts␈α∃are␈α∃needed␈α⊗for␈α∃an
␈↓ α∧␈↓epistemologically adequate representation of facts about machines.

␈↓ α∧␈↓␈↓ αT2.␈α∪Work␈α∪in␈α∪artificial␈α∩intelligence␈α∪is␈α∪still␈α∪far␈α∩from␈α∪showing␈α∪how␈α∪to␈α∪reach␈α∩human-level
␈↓ α∧␈↓intellectual␈α∂performance.␈α⊂Our␈α∂approach␈α∂to␈α⊂the␈α∂AI␈α∂problem␈α⊂involves␈α∂identifying␈α⊂the␈α∂intellectual
␈↓ α∧␈↓mechanisms␈αrequired␈αfor␈αproblem␈αsolving␈αand␈αdescribing␈αthem␈αprecisely.␈αTherefore␈αwe␈αare␈αat␈αthe
␈↓ α∧␈↓end␈α
of␈αthe␈α
philosophical␈α
spectrum␈αthat␈α
requires␈αeverything␈α
to␈α
be␈αformalized␈α
in␈αmathematical␈α
logic.
␈↓ α∧␈↓It␈α
is␈αsometimes␈α
said␈αthat␈α
one␈αstudies␈α
philosophy␈αin␈α
order␈αto␈α
advance␈αbeyond␈α
one's␈αuntutored␈α
naive
␈↓ α∧␈↓world-view,␈α∩but␈α∩unfortunately␈α∩for␈α∪artificial␈α∩intelligence,␈α∩no-one␈α∩has␈α∪yet␈α∩been␈α∩able␈α∩to␈α∪give␈α∩a
␈↓ α∧␈↓description␈α⊃of␈α⊃even␈α⊂a␈α⊃naive␈α⊃world-view,␈α⊂complete␈α⊃and␈α⊃precise␈α⊂enough␈α⊃to␈α⊃allow␈α⊃a␈α⊂knowledge-
␈↓ α∧␈↓seeking program to be constructed in accordance with its tenets.

␈↓ α∧␈↓␈↓ αT3.␈α∪Present␈α∪AI␈α∪programs␈α∪operate␈α∪in␈α∪limited␈α∪domains,␈α∪e.g.␈α∪play␈α∪particular␈α∪games,␈α∩prove
␈↓ α∧␈↓theorems␈α⊃in␈α⊃a␈α∩particular␈α⊃logical␈α⊃system,␈α⊃or␈α∩understand␈α⊃natural␈α⊃language␈α⊃sentences␈α∩covering␈α⊃a
␈↓ α∧␈↓particular␈α∂subject␈α∞matter␈α∂and␈α∞with␈α∂other␈α∞semantic␈α∂restrictions.␈α∞ General␈α∂intelligence␈α∂will␈α∞require
␈↓ α∧␈↓general␈αmodels␈αof␈αsituations␈αchanging␈αin␈αtime,␈α
actors␈αwith␈αgoals␈αand␈αstrategies␈αfor␈αachieving␈α
them,
␈↓ α∧␈↓and knowledge about how information can be obtained.

␈↓ α∧␈↓␈↓ αT4.␈α This␈α
kind␈αof␈αteleological␈α
analysis␈αis␈α
often␈αuseful␈αin␈α
understanding␈αnatural␈α
organisms␈αas
␈↓ α∧␈↓well␈αas␈αmachines.␈α Here␈αevolution␈αtakes␈αthe␈αplace␈αof␈αdesign␈αand␈αwe␈αoften␈αunderstand␈αthe␈αfunction
␈↓ α∧␈↓performed␈α⊃by␈α⊃an␈α⊃organ␈α⊃before␈α⊃we␈α⊃understand␈α⊃its␈α⊃detailed␈α⊃physiology.␈α⊃Teleological␈α⊃analysis␈α⊂is
␈↓ α∧␈↓applicable␈α∞to␈α∞psychological␈α
and␈α∞social␈α∞phenomena␈α∞in␈α
so␈α∞far␈α∞as␈α∞these␈α
are␈α∞designed␈α∞or␈α∞have␈α
been
␈↓ α∧␈↓subject␈α
to␈αselection.␈α
 However,␈αteleological␈α
analysis␈αfails␈α
when␈αapplied␈α
to␈αaspects␈α
of␈α
nature␈αwhich
␈↓ α∧␈↓have␈α
neither␈αbeen␈α
designed␈α
nor␈αproduced␈α
by␈αnatural␈α
selection␈α
from␈αa␈α
population.␈α Much␈α
medieval
␈↓ α∧␈↓science␈α
was␈α
based␈α
on␈α
the␈α
Judeo-Christian-Moslem␈α
hypothesis␈α
that␈α
the␈α
details␈α
of␈α
the␈α
world␈αwere
␈↓ α∧␈↓designed␈αby␈α
God␈αfor␈α
the␈αbenefit␈α
of␈αman.␈α The␈α
strong␈αform␈α
of␈αthis␈α
hypothesis␈αwas␈α
abandoned␈αat
␈↓ α∧␈↓the␈α⊂time␈α⊃of␈α⊂Galileo␈α⊃and␈α⊂Newton␈α⊃but␈α⊂occasionally␈α⊃recurs.␈α⊂ Barry␈α⊃Commoner's␈α⊂(1972)␈α⊃axiom␈α⊂of
␈↓ α∧␈↓ecology␈α"Nature␈αknows␈αbest"␈αseems␈αto␈αbe␈αmistakenly␈αbased␈αon␈αthe␈αnotion␈αthat␈αnature␈αas␈αa␈αwhole␈αis
␈↓ α∧␈↓the result of an evolutionary process that selected the "best nature".

␈↓ α∧␈↓␈↓ αT5. Novelty is not absolutely guaranteed.

␈↓ α∧␈↓␈↓ αT6.␈α
Behavioral␈α
definitions␈α
are␈α
often␈α
favored␈α∞in␈α
philosophy.␈α
 A␈α
system␈α
is␈α
defined␈α
to␈α∞have␈α
a
␈↓ α∧␈↓certain␈α∞quality␈α∞if␈α∞it␈α∞behaves␈α∞in␈α∞a␈α∞certain␈α∂way␈α∞or␈α∞is␈α∞␈↓↓disposed␈↓␈α∞to␈α∞behave␈α∞in␈α∞a␈α∞certain␈α∂way.␈α∞Their
␈↓ α∧␈↓ostensible␈α⊃virtue␈α⊃is␈α⊃conservatism;␈α⊃they␈α⊃don't␈α⊂postulate␈α⊃internal␈α⊃states␈α⊃that␈α⊃are␈α⊃unobservable␈α⊂to


␈↓ α∧␈↓␈↓ εu22␈↓ ∧



␈↓ α∧␈↓present␈αscience␈αand␈αmay␈αremain␈αunobservable.␈αHowever,␈αsuch␈αdefinitions␈αare␈αawkward␈αfor␈αmental
␈↓ α∧␈↓qualities,␈αbecause,␈αas␈αcommon␈αsense␈αsuggests,␈αa␈αmental␈αquality␈αmay␈αnot␈αresult␈αin␈αbehavior,␈αbecause
␈↓ α∧␈↓another␈αmental␈αquality␈αmay␈αprevent␈αit;␈αe.g.␈α I␈αmay␈αthink␈αyou␈αare␈αthick-headed,␈αbut␈αpoliteness␈αmay
␈↓ α∧␈↓prevent␈α∂my␈α∂saying␈α∂so.␈α∂Particular␈α∂difficulties␈α⊂can␈α∂be␈α∂overcome,␈α∂but␈α∂an␈α∂impression␈α⊂of␈α∂vagueness
␈↓ α∧␈↓remains.␈α
 The␈αliking␈α
for␈αbehavioral␈α
definitions␈αstems␈α
from␈αcaution,␈α
but␈αI␈α
would␈αinterpret␈α
scientific
␈↓ α∧␈↓experience␈α∂as␈α∂showing␈α∞that␈α∂boldness␈α∂in␈α∞postulating␈α∂complex␈α∂structures␈α∞of␈α∂unobserved␈α∂entities␈α∞-
␈↓ α∧␈↓provided␈αit␈αis␈αaccompanied␈αby␈αa␈αwillingness␈αto␈αtake␈αback␈αmistakes␈α-␈αis␈αmore␈αlikely␈αto␈αbe␈αrewarded
␈↓ α∧␈↓by␈α∩understanding␈α∪of␈α∩and␈α∪control␈α∩over␈α∪nature␈α∩than␈α∪is␈α∩positivistic␈α∪timidity.␈α∩ It␈α∪is␈α∩particularly
␈↓ α∧␈↓instructive␈α∩to␈α∪imagine␈α∩a␈α∩determined␈α∪behaviorist␈α∩trying␈α∩to␈α∪figure␈α∩out␈α∩an␈α∪electronic␈α∩computer.
␈↓ α∧␈↓Trying␈α↔to␈α↔define␈α↔each␈α↔quality␈α_behaviorally␈α↔would␈α↔get␈α↔him␈α↔nowhere;␈α_only␈α↔simultaneously
␈↓ α∧␈↓postulating␈α∞a␈α
complex␈α∞structure␈α∞including␈α
memory,␈α∞arithmetic␈α∞unit,␈α
control␈α∞structure,␈α∞and␈α
input-
␈↓ α∧␈↓output␈α⊂would␈α∂yield␈α⊂predictions␈α⊂that␈α∂could␈α⊂be␈α⊂compared␈α∂with␈α⊂experiment.␈α⊂ There␈α∂is␈α⊂a␈α⊂sense␈α∂in
␈↓ α∧␈↓which␈α
operational␈α
definitions␈α
are␈αnot␈α
taken␈α
seriously␈α
even␈αby␈α
their␈α
proposers.␈α
 Suppose␈αsomeone
␈↓ α∧␈↓gives␈α⊂an␈α∂operational␈α⊂definition␈α∂of␈α⊂length␈α∂(e.g.␈α⊂involving␈α∂a␈α⊂certain␈α∂platinum␈α⊂bar),␈α∂and␈α⊂a␈α∂whole
␈↓ α∧␈↓school␈α
of␈αphysicists␈α
and␈α
philosophers␈αbecomes␈α
quite␈α
attached␈αto␈α
it.␈α
 A␈αfew␈α
years␈α
later,␈αsomeone␈α
else
␈↓ α∧␈↓criticizes␈αthe␈α
definition␈αas␈αlacking␈α
some␈αdesirable␈αproperty,␈α
proposes␈αa␈αchange,␈α
and␈αthe␈α
change␈αis
␈↓ α∧␈↓accepted.␈α
 This␈αis␈α
normal,␈α
but␈αif␈α
the␈αoriginal␈α
definition␈α
expressed␈αwhat␈α
they␈αreally␈α
meant␈α
by␈αthe
␈↓ α∧␈↓length,␈αthey␈α
would␈αrefuse␈α
to␈αchange,␈α
arguing␈αthat␈α
the␈αnew␈α
concept␈αmay␈α
have␈αits␈α
uses,␈αbut␈α
it␈αisn't
␈↓ α∧␈↓what␈αthey␈α
mean␈αby␈α"length".␈α
 This␈αshows␈αthat␈α
the␈αconcept␈αof␈α
"length"␈αas␈αa␈α
property␈αof␈α
objects␈αis
␈↓ α∧␈↓more␈α
stable␈α
than␈α
any␈α
operational␈α
definition.␈α Carnap␈α
has␈α
an␈α
interesting␈α
section␈α
in␈α
␈↓↓Meaning␈αand
␈↓ α∧␈↓↓Necessity␈↓␈α∂entitled␈α∂"The␈α∂Concept␈α∂of␈α∂Intension␈α∂for␈α∂a␈α∂Robot"␈α∂in␈α∂which␈α∂he␈α∂makes␈α∂a␈α⊂similar␈α∂point
␈↓ α∧␈↓saying,␈α␈↓↓"It␈αis␈αclear␈αthat␈αthe␈αmethod␈αof␈αstructural␈αanalysis,␈αif␈αapplicable,␈αis␈αmore␈αpowerful␈αthan␈αthe
␈↓ α∧␈↓↓behavioristic␈αmethod,␈αbecause␈αit␈α
can␈αsupply␈αa␈αgeneral␈α
answer,␈αand,␈αunder␈αfavorable␈α
circumstances,
␈↓ α∧␈↓↓even a complete answer to the question of the intension of a given predicate."␈↓

␈↓ α∧␈↓␈↓ αT7.␈α∂Whether␈α∂a␈α∂system␈α⊂has␈α∂beliefs␈α∂and␈α∂other␈α∂mental␈α⊂qualities␈α∂is␈α∂not␈α∂primarily␈α∂a␈α⊂matter␈α∂of
␈↓ α∧␈↓complexity␈αof␈αthe␈αsystem.␈α Although␈αcars␈αare␈αmore␈αcomplex␈αthan␈αthermostats,␈αit␈αis␈αhard␈αto␈αascribe
␈↓ α∧␈↓beliefs␈α
or␈α
goals␈α
to␈αthem,␈α
and␈α
the␈α
same␈α
is␈αperhaps␈α
true␈α
of␈α
the␈α
basic␈αhardware␈α
of␈α
a␈α
computer,␈αi.e.␈α
the
␈↓ α∧␈↓part of the computer that executes the program without the program itself.

␈↓ α∧␈↓␈↓ αT8.␈α
 Our␈αown␈α
ability␈α
to␈αderive␈α
the␈αlaws␈α
of␈α
higher␈αlevels␈α
of␈αorganization␈α
from␈α
knowledge␈αof
␈↓ α∧␈↓lower␈αlevel␈αlaws␈αis␈αalso␈αlimited␈αby␈αuniversality.␈αWhile␈αthe␈αpresently␈αaccepted␈αlaws␈αof␈αphysics␈αallow
␈↓ α∧␈↓only␈α⊂one␈α⊂chemistry,␈α⊂the␈α∂laws␈α⊂of␈α⊂physics␈α⊂and␈α⊂chemistry␈α∂allow␈α⊂many␈α⊂biologies,␈α⊂and,␈α⊂because␈α∂the
␈↓ α∧␈↓neuron␈α∩is␈α∪a␈α∩universal␈α∪computing␈α∩element,␈α∪an␈α∩arbitrary␈α∪mental␈α∩structure␈α∪is␈α∩allowed␈α∪by␈α∩basic
␈↓ α∧␈↓neurophysiology.␈α∞Therefore,␈α∞to␈α∞determine␈α∞human␈α∞mental␈α∞structure,␈α∞one␈α∞must␈α∞make␈α
psychological
␈↓ α∧␈↓experiments,␈α␈↓↓or␈↓␈αdetermine␈αthe␈αactual␈αanatomical␈αstructure␈αof␈αthe␈αbrain␈αand␈αthe␈αinformation␈αstored
␈↓ α∧␈↓in␈α∞it␈α∂.␈α∞One␈α∂cannot␈α∞determine␈α∂the␈α∞structure␈α∂of␈α∞the␈α∞brain␈α∂merely␈α∞from␈α∂the␈α∞fact␈α∂that␈α∞the␈α∂brain␈α∞is
␈↓ α∧␈↓capable␈αof␈αcertain␈αproblem␈αsolving␈αperformance.␈α In␈αthis␈αrespect,␈αour␈αposition␈αis␈αsimilar␈αto␈αthat␈αof
␈↓ α∧␈↓the Life robot.

␈↓ α∧␈↓␈↓ αT9.␈α
Philosophy␈αand␈α
artificial␈α
intelligence.␈α These␈α
fields␈αoverlap␈α
in␈α
the␈αfollowing␈α
way:␈αIn␈α
order
␈↓ α∧␈↓to␈α∞make␈α∞a␈α∞computer␈α∞program␈α∞behave␈α∞intelligently,␈α∞its␈α
designer␈α∞must␈α∞build␈α∞into␈α∞it␈α∞a␈α∞view␈α∞of␈α
the
␈↓ α∧␈↓world␈α⊃in␈α⊃general,␈α∩apart␈α⊃from␈α⊃what␈α∩they␈α⊃include␈α⊃about␈α∩particular␈α⊃sciences.␈α⊃ (The␈α∩skeptic␈α⊃who
␈↓ α∧␈↓doubts␈αwhether␈αthere␈α
is␈αanything␈αto␈αsay␈α
about␈αthe␈αworld␈αapart␈α
from␈αthe␈αparticular␈αsciences␈α
should
␈↓ α∧␈↓try␈αto␈αwrite␈α
a␈αcomputer␈αprogram␈α
that␈αcan␈αfigure␈αout␈α
how␈αto␈αget␈α
to␈αTimbuktoo,␈αtaking␈αinto␈α
account
␈↓ α∧␈↓not␈α
only␈α
the␈α
facts␈α
about␈αtravel␈α
in␈α
general␈α
but␈α
also␈αfacts␈α
about␈α
what␈α
people␈α
and␈α
documents␈αhave
␈↓ α∧␈↓what␈αinformation,␈αand␈αwhat␈αinformation␈αwill␈αbe␈αrequired␈αat␈αdifferent␈αstages␈αof␈αthe␈αtrip␈αand␈αwhen


␈↓ α∧␈↓␈↓ εu23␈↓ ∧



␈↓ α∧␈↓and␈α
how␈α
it␈α
is␈α
to␈α
be␈α
obtained.␈α
 He␈α
will␈α
rapidly␈α
discover␈α
that␈α
he␈α
is␈α
lacking␈α
a␈α
␈↓↓science␈α
of␈αcommon␈α
sense␈↓,
␈↓ α∧␈↓i.e.␈α∞he␈α∞will␈α∞be␈α∞unable␈α∞to␈α∞formally␈α∞express␈α∞and␈α∞build␈α∞into␈α∞his␈α∞program␈α∞"what␈α∞everybody␈α
knows".
␈↓ α∧␈↓Maybe␈αphilosophy␈αcould␈αbe␈αdefined␈αas␈αan␈αattempted␈α␈↓↓science␈αof␈αcommon␈αsense␈↓,␈αor␈αelse␈αthe␈α␈↓↓science␈α
of
␈↓ α∧␈↓↓common sense␈↓ should be a definite part of philosophy.)

␈↓ α∧␈↓␈↓ αTArtificial␈α⊂intelligence␈α∂has␈α⊂a␈α∂another␈α⊂component␈α∂in␈α⊂which␈α∂philosophers␈α⊂have␈α⊂not␈α∂studied,
␈↓ α∧␈↓namely␈α∪␈↓↓heuristics␈↓.␈α∪ Heuristics␈α∪is␈α∪concerned␈α∪with:␈α∪given␈α∩the␈α∪facts␈α∪and␈α∪a␈α∪goal,␈α∪how␈α∪should␈α∩it
␈↓ α∧␈↓investigate␈α
the␈α
possibilities␈αand␈α
decide␈α
what␈α
to␈αdo.␈α
 On␈α
the␈α
other␈αhand,␈α
artificial␈α
intelligence␈αis␈α
not
␈↓ α∧␈↓much concerned with aesthetics and ethics.

␈↓ α∧␈↓␈↓ αTNot␈α∪all␈α∀approaches␈α∪to␈α∪philosophy␈α∀lead␈α∪to␈α∪results␈α∀relevant␈α∪to␈α∪the␈α∀artificial␈α∪intelligence
␈↓ α∧␈↓problem.␈α∞ On␈α∂the␈α∞face␈α∞of␈α∂it,␈α∞a␈α∞philosophy␈α∂that␈α∞entailed␈α∞the␈α∂view␈α∞that␈α∞artificial␈α∂intelligence␈α∞was
␈↓ α∧␈↓impossible␈α∂would␈α⊂be␈α∂unhelpful,␈α⊂but␈α∂besides␈α⊂that,␈α∂taking␈α⊂artificial␈α∂intelligence␈α⊂seriously␈α∂suggests
␈↓ α∧␈↓some␈α
philosophical␈αpoints␈α
of␈αview.␈α
 I␈αam␈α
not␈αsure␈α
that␈α
all␈αI␈α
shall␈αlist␈α
are␈αrequired␈α
for␈αpursuing␈α
the
␈↓ α∧␈↓AI goal - some of them may be just my prejudices - but here they are:

␈↓ α∧␈↓␈↓ β$9.1.␈αThe␈αrelation␈αbetween␈αa␈αworld␈αview␈αand␈αthe␈αworld␈αshould␈αbe␈αstudied␈αby␈αmethods
␈↓ α∧␈↓akin␈αto␈αmetamathematics␈αin␈αwhich␈αsystems␈α
are␈αstudied␈αfrom␈αthe␈αoutside.␈α In␈α
metamathematics␈αwe
␈↓ α∧␈↓study␈α∀the␈α∀relation␈α∀between␈α∪a␈α∀mathematical␈α∀system␈α∀and␈α∪its␈α∀models.␈α∀ Philosophy␈α∀(or␈α∪perhaps
␈↓ α∧␈↓␈↓↓metaphilosophy␈↓)␈αshould␈αstudy␈αthe␈αrelation␈α
between␈αworld␈αstructures␈αand␈αsystems␈αwithin␈α
them␈αthat
␈↓ α∧␈↓seek␈αknowledge.␈α Just␈αas␈αthe␈αmetamathematician␈α
can␈αuse␈αany␈αmathematical␈αmethods␈αin␈α
this␈αstudy
␈↓ α∧␈↓and␈αdistinguishes␈αthe␈α
methods␈αhe␈αuses␈α
form␈αthose␈αbeing␈α
studied,␈αso␈αthe␈α
philosopher␈αshould␈αuse␈α
all
␈↓ α∧␈↓his scientific knowledge in studying philosphical systems from the outside.

␈↓ α∧␈↓␈↓ αTThus␈α⊂the␈α∂question␈α⊂␈↓↓"How␈α⊂do␈α∂I␈α⊂know?"␈↓␈α∂is␈α⊂best␈α⊂answered␈α∂by␈α⊂studying␈α∂␈↓↓"How␈α⊂does␈α⊂it␈α∂know"␈↓,
␈↓ α∧␈↓getting␈αthe␈α
best␈αanswer␈αthat␈α
the␈αcurrent␈αstate␈α
of␈αscience␈αand␈α
philosophy␈αpermits,␈αand␈α
then␈αseeing
␈↓ α∧␈↓how this answer stands up to doubts about one's own sources of knowledge.

␈↓ α∧␈↓␈↓ β$9.2.␈α∂We␈α∂regard␈α∂␈↓↓metaphysics␈↓␈α∞as␈α∂the␈α∂study␈α∂of␈α∂the␈α∞general␈α∂structure␈α∂of␈α∂the␈α∂world␈α∞and
␈↓ α∧␈↓␈↓↓epistemology␈↓␈α
as␈α
studying␈α
what␈α
knowledge␈α
of␈α
the␈αworld␈α
can␈α
be␈α
had␈α
by␈α
an␈α
intelligence␈α
with␈αgiven
␈↓ α∧␈↓opportunities␈αto␈αobserve␈αand␈αexperiment.␈α We␈αneed␈αto␈αdistinguish␈αwhat␈αcan␈αbe␈αdetermined␈αabout
␈↓ α∧␈↓the␈α∃structure␈α∃of␈α⊗humans␈α∃and␈α∃machines␈α⊗by␈α∃scientific␈α∃research␈α∃over␈α⊗a␈α∃period␈α∃of␈α⊗time␈α∃and
␈↓ α∧␈↓experimenting␈αwith␈αmany␈αindividuals␈αfrom␈αwhat␈αcan␈αbe␈αlearned␈αby␈αin␈αa␈αparticular␈αsituation␈αwith
␈↓ α∧␈↓particular␈αopportunities␈α
to␈αobserve.␈α From␈α
the␈αAI␈α
point␈αof␈αview,␈α
the␈αlatter␈αis␈α
as␈αimportant␈α
as␈αthe
␈↓ α∧␈↓former,␈α⊃and␈α⊃we␈α∩suppose␈α⊃that␈α⊃philosophers␈α∩would␈α⊃also␈α⊃consider␈α∩it␈α⊃part␈α⊃of␈α∩epistemology.␈α⊃ The
␈↓ α∧␈↓possibilities␈α⊃of␈α⊂reductionism␈α⊃are␈α⊂also␈α⊃different␈α⊂for␈α⊃theoretical␈α⊂and␈α⊃everyday␈α⊃epistemology.␈α⊂ We
␈↓ α∧␈↓could␈α∂imagine␈α∂that␈α∂the␈α∂rules␈α∂of␈α∂everyday␈α∂epistemology␈α∂could␈α∂be␈α∂deduced␈α∂from␈α∂a␈α∂knowledge␈α∂of
␈↓ α∧␈↓physics␈αand␈αthe␈αstructure␈αof␈αthe␈αbeing␈αand␈αthe␈αworld,␈αbut␈αwe␈αcan't␈αsee␈αhow␈αone␈αcould␈αavoid␈αusing
␈↓ α∧␈↓mental concepts in expressing knowledge actually obtained by the senses.

␈↓ α∧␈↓␈↓ β$9.3.␈α
 It␈α∞is␈α
now␈α
accepted␈α∞that␈α
the␈α
basic␈α∞concepts␈α
of␈α
physical␈α∞theories␈α
are␈α∞far␈α
removed
␈↓ α∧␈↓from␈α∩observation.␈α∩ The␈α∩human␈α∩sense␈α∩organs␈α∩are␈α∩many␈α∩levels␈α∩of␈α∩organization␈α∪removed␈α∩from
␈↓ α∧␈↓quantum␈α∪mechanical␈α∪states,␈α∪and␈α∀we␈α∪have␈α∪learned␈α∪to␈α∀accept␈α∪the␈α∪complication␈α∪this␈α∀causes␈α∪in
␈↓ α∧␈↓verifying␈α
physical␈α∞theories.␈α
Experience␈α
in␈α∞trying␈α
to␈α
make␈α∞intelligent␈α
computer␈α∞programs␈α
suggests
␈↓ α∧␈↓that␈α⊂the␈α⊃basic␈α⊂concepts␈α⊂of␈α⊃the␈α⊂common␈α⊂sense␈α⊃world␈α⊂are␈α⊂also␈α⊃complex␈α⊂and␈α⊂not␈α⊃always␈α⊂directly
␈↓ α∧␈↓accessible␈α∂to␈α∂observation.␈α∂ In␈α∞particular,␈α∂the␈α∂common␈α∂sense␈α∂world␈α∞is␈α∂not␈α∂a␈α∂construct␈α∂from␈α∞sense
␈↓ α∧␈↓data,␈αbut␈αsense␈αdata␈αplay␈αan␈αimportant␈αrole.␈α When␈αa␈αman␈αor␈αa␈αcomputer␈αprogram␈αsees␈αa␈αdog,␈αwe


␈↓ α∧␈↓␈↓ εu24␈↓ ∧



␈↓ α∧␈↓will␈α⊃need␈α⊃both␈α⊃the␈α∩relation␈α⊃between␈α⊃the␈α⊃observer␈α⊃and␈α∩the␈α⊃dog␈α⊃and␈α⊃the␈α⊃relation␈α∩between␈α⊃the
␈↓ α∧␈↓observer and the brown patch in order to construct a good theory of the event.

␈↓ α∧␈↓␈↓ β$9.4.␈α
 In␈α
spirit␈α
this␈α
paper␈α
is␈α
materialist,␈α
but␈α
it␈α
is␈α
logically␈α
compatible␈α
with␈α
some␈αother
␈↓ α∧␈↓philosophies.␈α∂ Thus␈α⊂cellular␈α∂automaton␈α∂models␈α⊂of␈α∂the␈α∂physical␈α⊂world␈α∂may␈α∂be␈α⊂supplemented␈α∂by
␈↓ α∧␈↓supposing␈αthat␈αcertain␈αcomplex␈αconfigurations␈α
interact␈αwith␈αadditional␈αautomata␈αcalled␈α
souls␈αthat
␈↓ α∧␈↓also␈α∪interact␈α∩with␈α∪each␈α∩other.␈α∪ Such␈α∩␈↓↓interactionist␈α∪dualism␈↓␈α∩won't␈α∪meet␈α∩emotional␈α∪or␈α∩spiritual
␈↓ α∧␈↓objections␈αto␈αmaterialism,␈αbut␈αit␈αdoes␈αprovide␈αa␈αlogical␈αniche␈αfor␈αany␈αempirically␈αargued␈αbelief␈αin
␈↓ α∧␈↓telepathy,␈α
communication␈α∞with␈α
the␈α
dead␈α∞and␈α
other␈α
psychic␈α∞phenomena.␈α
 A␈α
person␈α∞who␈α
believed
␈↓ α∧␈↓the␈α
alleged␈αevidence␈α
for␈αsuch␈α
phenomena␈αand␈α
still␈α
wanted␈αa␈α
scientific␈αexplanation␈α
could␈αmodel␈α
his
␈↓ α∧␈↓beliefs with auxiliary automata.






































␈↓ α∧␈↓␈↓ εu25␈↓ ∧



␈↓ α∧␈↓α␈↓ αTREFERENCES

␈↓ α∧␈↓␈↓ αT␈↓αArmstrong,␈α∂D.M.␈↓␈α∂(1968),␈α∂␈↓↓A␈α∂Materialist␈α⊂Theory␈α∂of␈α∂the␈α∂Mind␈↓,␈α∂Routledge␈α∂and␈α⊂Kegan␈α∂Paul,
␈↓ α∧␈↓London and New York.

␈↓ α∧␈↓␈↓ αT␈↓αCarnap, Rudolf␈↓ (1956), ␈↓↓Meaning and Necessity␈↓, University of Chicago Press.

␈↓ α∧␈↓␈↓ αT␈↓αDavidson,␈αDonald␈↓␈α(1973)␈αThe␈αMaterial␈αMind.␈α␈↓↓Logic,␈αMethodology␈αand␈αPhilosophy␈αof␈αScienc
␈↓ α∧␈↓↓IV␈↓, P. Suppes, L. Henkin, C. Moisil, and A. Joja (eds.), Amsterdam, North-Holland.

␈↓ α∧␈↓␈↓ αT␈↓αGosper,␈α⊃R.W.␈↓␈α⊃(1976)␈α∩Private␈α⊃Communication.␈α⊃ (Much␈α∩information␈α⊃about␈α⊃Life␈α∩has␈α⊃been
␈↓ α∧␈↓printed␈α∩in␈α∩Martin␈α∪Gardner's␈α∩column␈α∩in␈α∪␈↓↓Scientific␈α∩American␈↓,␈α∩and␈α∪there␈α∩is␈α∩a␈α∪magazine␈α∩called
␈↓ α∧␈↓␈↓↓Lifeline␈↓).

␈↓ α∧␈↓␈↓ αT␈↓αLewis, David␈↓ (1974), ␈↓↓Counterfactuals␈↓.

␈↓ α∧␈↓␈↓ αT␈↓αMcCarthy,␈α→John␈↓␈α→(1959)␈α→Programs␈α→with␈α→Common␈α→Sense.␈α→␈↓↓Mechanisation␈α~of␈α→Thought
␈↓ α∧␈↓↓Processes, Volume I␈↓.  London:HMSO.

␈↓ α∧␈↓␈↓ αT␈↓αMcCarthy,␈αJ.␈αand␈αHayes,␈αP.J.␈↓␈α(1969)␈αSome␈αPhilosophical␈αProblems␈αfrom␈αthe␈αStandpoint␈αof
␈↓ α∧␈↓Artificial␈α∩Intelligence.␈α∪␈↓↓Machine␈α∩Intelligence␈α∩4␈↓,␈α∪pp.␈α∩463-502␈α∩(eds␈α∪Meltzer,␈α∩B.␈α∩and␈α∪Michie,␈α∩D.).
␈↓ α∧␈↓Edinburgh: Edinburgh University Press.

␈↓ α∧␈↓␈↓ αT␈↓αMcCarthy,␈α⊂John␈↓␈α⊂(1976),␈α⊃␈↓↓First␈α⊂Order␈α⊂Theories␈α⊃of␈α⊂Individual␈α⊂Concepts␈↓,␈α⊃Stanford␈α⊂Artificial
␈↓ α∧␈↓Intelligence Laboratory, (to be published).

␈↓ α∧␈↓␈↓ αT␈↓αMontague,␈α↔Richard␈↓␈α_(1963),␈α↔Syntactical␈α↔Treatments␈α_of␈α↔Modality,␈α↔with␈α_Corollaries␈α↔on
␈↓ α∧␈↓Reflexion Principles and Finite Axiomatizability, ␈↓↓Acta Philosophica Fennica␈↓ ␈↓α16␈↓:153-167.

␈↓ α∧␈↓␈↓ αT␈↓αPutnam,␈α∞Hilary␈↓␈α∞(1961)␈α∞Minds␈α∞and␈α∞Machines,␈α∞in␈α∞␈↓↓Dimensions␈α∞of␈α∞Mind␈↓,␈α∞Sidney␈α∞Hook␈α∞(ed.),
␈↓ α∧␈↓Collier Books, New York.

␈↓ α∧␈↓␈↓ αT␈↓αRyle, Gilbert␈↓ (1949), ␈↓↓The Concept of Mind␈↓, Hutchinson and Company, London.

␈↓ α∧␈↓John McCarthy
␈↓ α∧␈↓Artificial Intelligence Laboratory
␈↓ α∧␈↓Stanford University
␈↓ α∧␈↓Stanford, California 94305











␈↓ α∧␈↓␈↓ εu26␈↓ ∧