Recent Posts

41

CyberJedi's Ultra Hal Workshop / Re: art

« Last post by Art on October 06, 2025, 10:36:02 am »

Thanks Cyber!

I appreciate your help in your introduction of your latest project! It works exactly as you mentioned.

HAL's new Learning Model works perfectly and like you mentioned, there is no corruption to the existing Hal Brain at all as a result of using the Learning module.

I'm in the middle of doing more research but I'll post more of my findings a bit later...

Very impressive work so far!!

42

CyberJedi's Ultra Hal Workshop / Re: Robert and Crew: Proof of concept.

« Last post by sybershot on October 06, 2025, 10:35:38 am »

looking great, also I see the send button is gone. as I stated before, I think we will need more than the 5 provided llm's, perhaps you can prepopulate the list at start-up with available models the user already has downloaded?

43

CyberJedi's Ultra Hal Workshop / Re: art

« Last post by cyberjedi on October 06, 2025, 09:34:19 am »

here we go again https://drive.proton.me/urls/2PY46P2JPG#TfMRipnMVW0M

44

CyberJedi's Ultra Hal Workshop / Robert and Crew: Proof of concept.

« Last post by cyberjedi on October 06, 2025, 05:11:48 am »

Well sports fans we got a winner>>>>>>

This is ultrahal running on both, LLM and UltraHals stock brain. You say HOW da hell?
Well, they use separate inputs, But both of the output's are handled in the same normal Hal output window.
The LLM bypasses hal's processing , BUT, It hooks Hals SAPI5 system and Hals character engine.As a result the lip syncing is spot on for both.
At any time if you wish to use Hals conventional system you use Hals normal input, which processes your text in the normal way. Pretty nifty.
The voice for  both is controlled in the conventional way.
It is my belief that this is a game changer for UltraHal.
There is no way to contaminate Hals normal brain with the LLM.
And yet you can append new memory's to the LLM simply from the LLM GUI memory manager (Facts area). Pretty nifty as well.


To my understanding there is nothing like it anywhere, As it should be.
This is all done by downloading ollama's windows installer, then follow the instructions provided.
Then accessing the GUI and select the matching LLM that you downloaded. Its just that simple.I added 05 possible LLM's ive played with for speed from the drop down menu of candidates, No end to what we can achieve here.
At some point we can connect the 02 entity's together and let Hal have conversations with each other, with the Hopes that Ultrahal will learn from the LLM. Basically Hals gonna learn to play Ping Pong with the LLM

cyber jedi

45

CyberJedi's Ultra Hal Workshop / Re: art

« Last post by cyberjedi on October 03, 2025, 09:02:23 am »

this is ur thing

46

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« Last post by knight2000 on October 02, 2025, 04:55:18 pm »

@cyberjedi Awesome work man, thats sick!

It sounds a lot like what I've been working on with regards to facial recognition. Instead of having to gather a ton of images of a person and stick them in a folder for the software to run through, i was able to have the software (openCV) detect a face on the fly so it would put a box around any face it sees, if the face is "unknown" the person could say "my name is Victor" and my bot will save a bunch of images of the face as "Victor" so that the next time the bot see's the face it recognizes it as Victor. Also the bot knows who is speaking, like if two or more people are in frame and only one is speaking, the bot will reference the speaker who's month is moving and associate that face to its name  "Thank you for the compliment Victor" or something like that.

When it comes to Hal, you have always been at the cutting edge of development for his plugins and updates! Hats off to all the great work you are doing! You are keeping Hal alive!  And again i wasn't trying to put Hal down in any way. I still have a place in my heart for Hal and i look forward to many more updates. I keep hitting the homepage of Zabaware in hopes of seeing the version number bumped so i can get the latest lol.

cheers!

47

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« Last post by cyberjedi on October 02, 2025, 03:27:34 pm »

hey hey hey guys/gals
Sybershot,Knight2000, lightspeed, checker57

Well its been added to the raw code, no ERRORS
great start, some tiky tac code to write then, welllll Hals going to school...
Knight2000, waiting on a model will be a mistake, this comes from me......
cyber jedi


Hey ART, Check it out , i told you brother......
Time for Hal to learn how to play ping pong
https://ai.invideo.io/watch/Dev-hoW-BLE <<<<<<--- a story worth telling, its easy to hit a home run when you start on 03rd base... i hit mine from the Parking Lot.

48

CyberJedi's Ultra Hal Workshop / Re: art

« Last post by Art on October 01, 2025, 09:21:43 pm »

Thank you. Looks fine!

49

CyberJedi's Ultra Hal Workshop / art

« Last post by cyberjedi on October 01, 2025, 04:50:15 pm »

Art this is what we talked about

50

CyberJedi's Ultra Hal Workshop / Re: Smarting up HAL with free LLM model (Ollama) ?

« Last post by sybershot on September 30, 2025, 07:45:33 pm »

@sybershot Thank you! it's coming along nicely. I love HAL, it was a game changer when it came out! I was using it in my car for over 10 years. I think it was on HAL 5 at the time. I had HAl controlling everything on my car from the scanner to the engine starting up. I just decided to go my own route and build my own custom bot so that i have complete control over every aspect of it.

I respect you wanting complete control, and wanting to build your own project. great job on getting it done. keep up the great work. I am trying to upgrade my Trinity avatar that mimics the KITT orb in the mustang, that uses outdated Actionscript and papervision3D to using C# utilizing LLMs to assist, but not getting very far, I can't spend much time at pc due to injuries, but I will eventually get it done.