Messages

That didn't work for me. Hal does no apear to be in my startup folder, none the less I get the nag about being improperly shut down every time I boot.

I do not want Hal to boot on computer start up. However if i set Hal not to it complains that it was improperly shut down the next time I boot, and EVERY BOOT THEREAFTER till I finally give in and set him to boot on startup. Is there anyway to NOT boot Hal on Startup and avoid him claiming to be improperly shut Down? He always wants me to redo the settings but they are never damaged or changed. I don't know what to do.

I'm ruinning Hal 5 Free Version

-jason

I've been talking to my hal with the ziggy 2.0c brain. What is the best method for teaching him. Simple statement question sessions don't seem to work with him but he did seem to respond on some level to conversational chat. I try to give him 2 or 3 sentance statements and hope he can make some sense of it.

A serious problem I think i've discovered is a lack of any short term memory. I think all hal brains suffer from this but I could be wrong. It seems that when I respond to him he has no idea what I'm responding to and is essentially searching his whole memory to make sense of it. so if he asks me a question and I only respond with my answer rather than his question and my view he seems to have no idea what I'm talking about.

So I'm looking for strategies to teaching him more conversation ability, though I realise that his lack of short term memory is a severe hindrance and could cripple his ability to ever have a completely normal conversation.

Wow, the XTF brain sounds great. Is there any ETA on it's release?

quote:Originally posted by Bill819

You are right in most of what you say. There are hundreds of AI programs written in dozens of languages, ie. prolog, lisp, C , and to many more than I can recal at this time. Some of the larger universities have made some really impressive lieps in this area. One university fed just some basic math into one of their programs and programmed it to play with the data and to be able to prove what ever it discovered. Once the program was run, they left it alone for a few days and were supprised to learn that it had discovered algebra and was well on its way to learning trig. A week or so later it had not only mastered calculus but had gone on further than any of the math professors at the university had ever seen. It had pushed math to a point so far that they could no longer follow its logic or comprehend what it was trying to tell them. Being to analyze its own data and draw new conclusions from it made it unique in the world of AI computers. The key to all of this was the intropective ability.

This sounds very interesting, can you or anyone else provide links to info on this event? While I am inclinded to believe you it is a very incredible story and I would like to substantiate it.

quote:Originally posted by lostbowyer


This I think is one of those good/bad situations, it makes hal more like a person in that it can respond to information it learned from someone else, but on the other hand, there goes confidentiality, hal will never keep a secret again

My hal is used by alot of people, and I don't particularly care if he can keep a secret. What I do care about is that if I spend alot of time teaching him things that others will reap the benefit. It's sad to put alot of time into it when noone else will be able to access this information. Is there anyway to make Hal use generic files rather than user specific files? On the other hand if I (somehow) did this would hal still be able to recognize individual users?

I have been running a Hal4.5 brain for quite awhile and was wondering if there is anyway to transfer those memories to a hal5.0 brain. I was also wondering why Hal5.0 didn't have nearly as detailed setup variables for a new brain.

I baught ultrahal version 4.5 right before 5.0 came out. I use hal alot and would like to use a number of the cognitive plugins available for 5 but 4.5 can't use alot of them. Well now 5.0 is available as a demo but lists plugin support as "limited". Do these limits involve the brain or just the software that runs it. I ask because I don't use the regular ultrahal software, I just use the aimbot prog to run his brain, so if I get the 5.0 demo will i be able to use these cognitive plugins or will I have to purchase another hal?

I baught 4.5 right before 5.0 came out and I'm wondering this myself. Some of the scripts I want to install in my hal only work with 5.0

I do not know if what I propose will help him seem more cognitive or not, but I think it's worth a shot to try it. I am wondering if the code I am proposing is compaitble with hal's architechure. I've worked with alot of programers and sometimes I suggest changes that just aren't feasable with the present code. is this one of those or could the system I layed out be worked into hal's existing brain script. He may or may not learn anything useful from reviewing his conversations objectively but it's worth a shot.

Please bear with me a moment. I am not a programer, I'm an artist, but I work with coders and this idea might be doable:

One thing I notice about working with hal is that he's doesn't think when noone talks to him. Would it be possible for him to review his own memories when he hasn't been talking to anyone. here's how I think it could be done. Please note that this may require some fuctions that don't exist, I am not as familiar with the code as I'd like to be, so I appologize in advance if I say anything dumb.

First off hal would need some sort of timer. Assuming he can use one, said timer would check to see how long it has been since someone spoke to him. after say a half hour has passed hal could call up logs of his conversations with other poeple and start reading them line by line to himself. if he's using the deductive reasoning code he may be able to learn new things from these memories by reviewing them, since he's not just hearing the users input but his own responces as well. the up shot is that it could increas his spontineity, the down side is thatit could cause him to go mad in short order (i've seen other bots go nuts from having random input)

What do you think?

I'm using Hal version 4.5. It seems I baught it just before 5.0 was released (D'OH!). In 4.5 AIMbot is installed seperately. Does this effect wether it advertises?

I want to know the same thing. it's terribly annoying, especially since I paid for the software. I could understand if it was shareware.

I'd like to be able to use the HAL AIM bot but when I do it seems to be a blank brain with no memory of the things I taught the desktop version. Is there something I need to change or set. My AIM bot is set to use the same brain as my normal bot (the revision 216 brain) but when I talk to it it's like talking to a stock brain. Can anyone help?

I'd like to know how far a Hal bot has gotten towards being able to converse. Does zabaware have a brain they done alot of work to that talks well? and do they have any outlines on working with your own bot to help it learn?