Tues.27.JUL.2010 -- Default "IS" in BeVerb
Yesterday our work was drawn out and delayed
when we discovered that the AI could not
properly recognize the word "YOURSELF."
The AI kept incrementing the concept number
for each instance of "YOURSELF". Since we
were more interested in coding who-queries
than in troubleshooting AudRecog, we
substituted the sentence "YOU ARE MAGIC"
in place of "YOU ARE YOURSELF".
Even then the AI did not function perfectly
well. The chain of thought got trapped in
repetitions of "ANDRU AM ANDRU", until
KbTraversal "rescued" the situation. However,
we know why the AI got stuck in a rut. It was
able to answer the query "who are you" with
"I AM ANDRU", but it did not know anything
further to say about ANDRU, so it repeated
"ANDRU AM ANDRU". Immediately it made us want
to improve upon the BeVerb module, so that
the AI will endlessly repeat "ANDRU IS ANDRU"
instead of "ANDRU AM ANDRU". Therefore let us
go into the source code and make "IS" the
default verb-form of the BeVerb module.
midway @ t @ DO \ search backwards in time; 27jul2010
I 0 en{ @ 66 = IF \ most recent instance; 27jul2010
66 motjuste ! ( default verb-form 66=IS; 27jul2010 )
I 7 en{ @ aud ! \ get the recall-vector; 27jul2010
LEAVE \ after finding most recent "IS"; 27jul2010
THEN \ end of test for 66=IS; 27jul2010
-1 +LOOP \ end of retrieval loop for default "IS"; 27jul2010
The upshot was that the AI started repeating
"ANDRU IS ANDRU" instead of "ANDRU AM ANDRU".
Unfortunately, however, the AI also started
repeating "I IS I".
Tues.27.JUL.2010 -- Tweaking a Few Parameters
Next we spent quite some time searching for
some sort of quasi-werwolf mechanism that would
re-activate the last concept in a thought as the
first concept in a succeeding thought. We searched
our code in vain for a variable that would keep
track of any resuscitand concept. We looked at
our ActRules page and we re-studied our Moving Wave
Algorithm. Then it dawned on us. The Moving Wave
automatically leaves the cresting, final concept
active. No Werwolf mechanism is necessary. If we
want to avoid the repetition-chanting of "ANDRU
IS ANDRU", we have to make the "qutop" query-topic
have a resuscitand activation of, say, forty (40),
so that it will be higher in activation than the
level of thirty-six (36) typically left on the final,
cresting concept in a sentence of normal thought.
So we comment out the old setting of "16" for
"qutop" in the WhoPlex code as shown below, and we
use a value of "40".
: WhoPlex \ initial stub; may be moved; 26jul2010
1 t @ 1 + DO \ loop in search of qutop; 26jul2010
I 0 psi{ @ qutop @ = IF \ seek qutop; 26jul2010
\ 16 I 1 psi{ ! \ activate qutop; 26jul2010
40 I 1 psi{ ! \ activate qutop; 27jul2010
THEN \ end of test for query-topic; 26jul2010
-1 +LOOP \ end of loop seeking qutop; 26jul2010
; ( End of WhoPlex; return to EnCog )
Now we run the AI and we ask it, "Who are you?"
Transcript of AI Mind interview at
0 24 7 o'clock on 28 July 2010.
Human: who are you
Robot: I AM ANDRU
Human:
Robot: I AM ANDRU
Human:
Robot: ANDRU HELPS KIDS
Human:
Robot: KIDS MAKE ROBOTS
Human:
Robot: ROBOTS NEED ME
Human:
Robot: I IS I
Human:
Robot: I AM ANDRU
Human:
Robot: ANDRU HELPS KIDS
Human:
Robot: KIDS MAKE ROBOTS
User Command: halt
For the first time in our dozen-plus years of
developing MindForth, the AI acts like an
intelligence struggling to express itself,
and it succeeds admirably and fascinatingly.
We run the robot AI through its cognitive paces.
We tell it things, and then we ask it questions
about its knowledge base. We seem to be dealing
with a true artificial intelligence here. Now we
upload the AI Mind to the World Wide Awakening Web.
Mentifex
--
http://www.scn.org/~mentifex/mindforth.txt
-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244&id_secret=8660244-6e7fb59c
Powered by Listbox: http://www.listbox.com
