My experience so far

[MikeA]

Just to bore you all again with my posts!

Well, been experimenting a bit. I deleted the entire mainQA section and a few other sections that contained random facts.

Seems I've sent Hal a bit funny. Now its mostly insults. Strangely this didn't happen at first, but now almost everything is preceded with an insult. I wonder where that comes from?

Here is one:

"I believe in respect for the dead; in fact I could only respect you if you were dead. Hi Mike. Any evening plans?"

Nice eh?

Sorry to say this, but what I am realising is that Hal without complete tuition is a bit of a fake. I mean, the advantage of Hal over ALICE is the ability to learn. But it appears that it is all dependent on using a whole bunch of random knowledge to look smarter. Insults are funny, but they should be an optional addon. Same with the dictionary and other set random phrases.

I will experiment a bit more, but now I realise the difference between Hal and ALICE is that Hal has an enormous amount of nonsense in its brain that suggests it knows more than it does. The annotated ALICE is more straight-forwards with its info.

What seems to be an ideal solution would be the ALICE brain info, with the Hal ability to learn through speech input.

Hal would make a lot more sense to me if it started with a blank brain, except for the basis of speech, salutations, question forms, etc. And then it would be clear that it would learn.

What I find myself doing is wanting to correct Hal often. But as far as I know there is no 'bad answer' function (there's an ALICE addon for that). This is something extremely important with so much random info in Hal. There needs to be correction. I can use IF / THEN but that doesn't tell Hal the reply was incorrect.

Feel free to tell me I'm an idot and have completely missed the point. I would like to get more into Hal, but I can't get past the fact that it is all too unreal. Having compared Hal to a new ALICE setup, there is no comparison. The ALICE bot was simplying parroting of course, but it made sense in the context. Plus it understands IT and THAT.

I wonder if there is a desktop ALICE.........

[Art]

MikeA,

I understand what you're saying but the compilation of all the assorted fact upon which Hal can draw only adds to the suspension of disbelief, or more realistic approach. The more material the more semblance of knowledge (real or assumed).

Hal a bit of a fake? Then just what is ALICE? Be careful...you don't have the home field advantage here.

The insults you experienced were only a result of you "tweaking" with Hal's data files. Kind of like you having a partial lobotomy then trying to discuss physics, Shakespeare or Quantum mechanics. Oddly, a lot of people who have experienced severe head trauma have often been heard using vile language and cursing, yet before the accident they were quite kind and gentle people.

Alice will most certainly reply in a fixed, anticipated manner because that is all it knows how to do. It only looks for a word or statement that fires a trigger word or phrase then selects a response that has been written by a "Botmaster". As far as I know, this is the only way for an AIML type of bot to "learn"...whenever it's "Botmaster" supplies it with new knowledge.

Might be fine for an expert system (knowing all about one particular subject), but I really think the bots like Hal offer the element of surprise when they come up with something that you had completely forgotten about (sometimes months ago) or just created an observation that was spot on with regard to the current conversation.

To me, it's those little snippits of knowledge or humor that bring a smile to my face or make me raise an eyebrow.

To each their own, but for now, I'll stick with Hal.
[8D]

[jasondude7116]

ditto art[]

these "problems" you are talking about can be modified in an almost limitless fashion with Hal. which, i guess could be done with aiml.

the difference is, that however currently limited, Hal has a form of "intelligence". i.e. there is some reasoning to a response versus just trigger. (i know i am simplifying it)

what i like about Hal is the general structure. Some people, however might want more "normal human type" responses. i like the fact that my ability to expand hal is almost limitless. aiml could be treated the same way, except in it's current form it does less "thinking" than hal.

I personally don't care as much (for the purposes of my a.i.) if the response makes clear sense to a human, but if there was thought involved. i think some of the things you are talking about are happening because the script has been tweaked in a way that makes it happen. the anger responses should only trigger when a state of anger exists from detection of "angry comments" towards Hal. the detection can be modified in the brain. you might also want to try either O.T.C.E.'s emotions plugin or my version, it keeps track of emotions for multiple users over time. with this plugin, the emotions are not instant and temporary like in default Hal. it might be that because the "anger" detection is not set up for you properly, the anger emotion is triggered at the wrong time.

-just my 2 cent[]
-the dude

[Cefwyn]

I've just decided to lobotomist my hal as well
I didn't delete the mainQA table itself and instead deleted all it's entries just in case somewhere in script it's reference, and so far I've not had anything unusual happen. Unfortunately without those QA responses it becomes very obvious when it starts parroting things I've typed to it before as it instead makes up questions using whatever I last said to it and adding a question mark at the end, which doesn't always make a lot of grammatical sense. This tells me at least, that without the QA brain hal would be quite boring, but I also feel that there should be a little less reliance on the QA brain as it often does quite well just using stuff you've taught it. However if you do that then where is the good balance between unexpected answers which pertain to your conversation and information that you have taught it? I found ALICE to be to be way too predictable and I'm quite happy with hal. Does that mean there isn't anything I would like to change? No, but many of the changes I've thought about would be quite difficult to do, and then others I probably will get around to writing plugins for.

EDIT: Without the QA brain, hal also seems more inquisitive about my responses, so it could actually accelerate my teaching process, though it definitely limits hals appearance of knowledge for now.

[Bill819]

To MikeA and others who may not be satisfied.
A few years ago someone and I think it was OTC wrote a small program to interface Alice with Hal. Once it was installed you could run both programa at the same time, go away and let them talk all day and night if that is what you wanted. In this way Hal eventually was suppose to learn much of what Alice had been programmed with. If you think that Alice contains a lot of real data as opposed to Hal then maybe you should see if OTC and make the connection work witht the new Hal.
Bill
P.S.
One mans trash is anothers treasures. You can't please everyone all the time.

[MikeA]

Wow.... didn't expect such a response.

I should say I have no problem with the insults as I appreciate that was caused by messing around with the brain.

Regarding AIML, I only have a little knowledge of it but I am not a fan of the principal of it (the fact that a large amount of response are simply fixed q + a responses in the code).

I'm also not sure I'm a fan of the random knowledge idea either. The learning angle of Hal is a great idea. But I don't know and would never say half the things in the mainQA, nor would anyone I know. And I suppose I am not interested in Hal knowing a bunch of stuff uncontrolled by me. And the mainQA is really only like AIML in that it is a static list.

I think my point is, if the mainQA was based on the top 10,000 common sense questions (or top 1000), then it might make more sense as far as being a brain. Or if it was empty and HAL could be taught from scratch (which seems not to work). At the moment, it's like a learning AI attached to a slightly bizarre dictionary.

I have downloaded this for free, so I am not the slightest bit unhappy with it. It has been an very interesting experience. But I just feel a great idea, and enormous potential for a desktop AI has been lost a little by this mainQA approach of random info.

I was going to try the XTF v1.2 brain today but so far I can't get it to work with hal 6.2.

Anyway, thanks for the thoughtful replies.

[Dollar]

>>I've just decided to lobotomist my hal as well <<

can someone who can comprehend this situation of spelling??
Didnt One talk about this?

[Art]

The XTF brain was for an earlier version (5.0) of Hal and will not work with 6.X

There should be an individual section somewhere in the Forum for version 5 items and version 6 items.
Sometimes the two can be interchanged but more often not.

[Cefwyn]

quote:Originally posted by Dollar

>>I've just decided to lobotomist my hal as well <<

can someone who can comprehend this situation of spelling??
Didnt One talk about this?

I apologize for my horrendous spelling typo []
Do some degree it is still correct. A lobotomist is a doctor who performs lobotomies, and so as I performed a lobotomy on hal, that makes me a lobotomist. Therefore I decided to act as a lobotomist towards hal. The original sentence wasn't fully grammatically correct, but still in essence had the right meaning. Definitely more grammatically correct then your question, I must say[]

MikeA: yesterday while I was searching through the forum I came across a Hal 6.0 updated version of the XTF brain. I think it was fixed by OnTheCuttingEdge. I'm pretty sure either it was in his D.A.V.I.D. project plugins thread or a thread linked from that one.

[One]

I decided, I will typist my Hal. []

[Cefwyn]

That's a rather cruel and unusual thing to do to a poor, and defenseless bot. You should be ashamed, and I hope you get carpal tunnel syndrome from all your typistry