Topics

1

Ultra Hal Assistant File Sharing Area / What is Suitable for 6.2?

« on: March 03, 2010, 01:09:54 pm »

Hi All

Been a while since I've been here. Just got back into using Hal. As I mentioned in a post (ages ago) I've emptied the mainQA and some other tables with 'parrot' responses to see what will happen. I hoping to create a more AI focused Hal, perhaps less smart due to no mainQA, etc responses to use, but hopefully more natural. We will see.

Anyway, I'm a bit confused about plugins. I have had trouble using a number of them, but wonder which are suitable / useful for version 6.2.

Would love to know if there are any particularly that AI lovers feel they could not do without.

Will also report back my own findings.

Mike

2

Ultra Hal 7.0 / My experience so far

« on: March 23, 2009, 01:07:05 pm »

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.........

3

Ultra Hal 7.0 / Shortcuts [:)]

« on: March 21, 2009, 04:24:35 am »

Hi again (my third post in 5 minutes)

One more thing, that I felt should be in a separate topic.

I just read a post from a longer term member about new users wanting to take shortcuts. I imagine that's very true.

However, I find having to start from zero while testing Hal to be a bi counter-productive. I understand in the long term the point is to teach Hal from scratch. However, for evaluation purposes, it would be good to start with a, say 6-month old system.

I understand that means it won't have my personality, but that would be fine (in fact better ). There are a whole range of basic responses that, probably if you compared all the brains of the longer term users, would probably be consistent amongst them, to some degree.

Would it not be worth having such a brain available to download, that could then be built on for either those that want a better evaluation, or simply those that, due to time constraints, maybe want to take an initial shortcut (while understanding the implications of that).

Is there such a brain download available?

Thanks.

4

Ultra Hal 7.0 / The content of the brain mainQA?

« on: March 21, 2009, 04:03:16 am »

Hi all

Just started with this. Trying to get my head around it. I didn't post this in 'programming the brain editor' as I thought it was a more general question.

I feel I may be missing something, but I just can not see the point to the info in the mainQA area of the Ultra Hal 6.2 brain at all. I have had a look through the questions and answers in the brain editor, although I probably only saw about 10% of what is there.

Most of the questions I saw are quite obscure topics (i.e. "bikini wax" ), or simply irrelevant to most normal conversation. Is there a reason for this? Am I missing something? I just don't really see how random responses of obscure topics to recognised words is beneficial to the communication.

For example, I asked Hal 'What is the opposite of hot?' (just as a test to see what info was already there). The response was something like 'In Virgina in spring many people...... ' (or something that obscure). Couldn't work out where that response came from until I took a look at the mainQA section of the brain editor.

Would love to hear if it is just me, or if others find the content of this section equally strange. I'm currently deleting all the rows to see if the communication (after a bit) will be more realistic.

One last thing. When purchased, is the save feature unlocked in the brain editor?