[Snowman]

The Clavichord seriously needed a piezo pickup on it.. and a nice amp. Mozart really needed an amp on that thing.

Then there's the Hurdy Gurdy. It looks like whoever invented it had a weird imagination. No offense intended.

Then there's the Nyckelharpa.

[Art]

The longer I listened, the more I was amazed at his versatility with the instrument. Nice find Aaron!

[Snowman]

Hello beautiful people  . Here's another iteration of my update videos.

I added two more editors to the program; a database editor and script editor. I want to add another editor for the Avatar/UI profile. I also want to create a color coder for the script editor and a skin editor for the upcoming Avatar editor, but, those are more of a luxury addition, so they are lower on my priority list. After the editors are complete, I need to start adding content, laying out the a.i. internal structure. 

On another note: Next week, I'm supposed to get my wisdom teeth taken out.     I guess I won't be as wise any more, so please overlook any future foolishness on my part. 

Later... and may the forth be with you.

[Korrelan]

Liking the user interface so far… It’s all looking very slick, and kinda retro, deffo reminds me of MS DOS (which I still have to use frequently in my work).

Hope you have some ideas for the AI portion, though your interface with a Chatbot engine would be cool.

Just wanted to say nice work, I can see the dedication and time spent. 

[Snowman]

Thanks. I like the old-school look and feel too. I'm trying to keep the creativity and color in an otherwise logic heavy project.

I have so much ai engine stuff in my head.. and have already written most of it. I would describe it out here but my head is currently full of editor stuff. 

I focus on one thing at a time..

 

[squarebear]

I like it too. A great retro 8 bit days feel.

[Snowman]

I think I've technically finished my User Interface. I got all the major editors finished. Now it's time to move on to the AI engine implementation. I've already laid out some of it, but now it's the time to focus on it.

After that, I need to start adding more significant content. Next, I will need to start thinking about software distribution.

I hope everyone is doing well.

P.S. for those interested in the Harpejji I am working on; I am waiting for enough money to buy some guitar coils. I was using a piezo pickup, but it was picking up too much feedback. It didn't sound right either. A regular guitar pickup should fix this. I'll need five or six pickups to pick up all the strings. It looks nice.

[Art]

Aaron,

Saw the video and am glad you have pretty much nailed down the interface.

Are you planning for it to be able to "learn" from conversations or from other sources like reading from a text file or passage?

Will the database be user editable?

Will it have emotions?

Will it want to take over the world?

Will it have Documentation?

Let Will ask any other questions. Heh!!

Get to hear your progress is ... progressing.

[Snowman]

Are you planning for it to be able to "learn" from conversations or from other sources like reading from a text file or passage?

The Node editor currently has a conversation parser. So you can easily write a fictional conversation or paste a real one between two people there. However, the input will be parsed line by line. The User statement will be on the odd lines while the Ai response will be on the even ones. A person could potentially feed it tons of different conversations so that it would broaden Athena's response options.

As for extrapolating random information from a text file, I have nothing set up right now. Naturally, there will be some extrapolating from the user's statements, but learning that information will have an intended purpose. I really don't want Athena to learn a bunch of useless knowledge as it's main focus. That would probably lead to random odd responses from her. (I know people who do that. People who randomly say weird stuff that has little or no bearing to the current conversation.) Unless, of course, you are really into that.   Did you know some chickens have murderous intentions?

Will the database be user editable?

From the database editor you can currently edit any database. In my video I displayed the Options Dialog. It allows for a specific database, brain script, avatar, and other options that will only be associated with a specific user. Although, I haven't done this yet, I could have Athena ask the user's name before every conversation (or an option to do that). That way Athena can automatically use the specific User's settings. Maybe she can even ask for a password. That way, if you've told Athena things that is a secret only between you and her, she will keep that secret if another person is talking to her. Any suggestions?

Will it have emotions?

It would make conversations a lot harder to write, but a lot more interesting. I intend for her to have them. HOWEVER, perhaps emotions shouldn't be associated with vital information. If she was supposed to remind you to take medication, but, she was also very angry with you , perhaps for her to suddenly forget that appointment, it would be a very 'bad idea'. Since she really isn't meant to be an assistant, perhaps she should 'conveniently' forget things. Maybe let that be a lesson why you shouldn't tick off your Chatbot  . Any thoughts on this? By the way, this is a real thing, I could definitely program this at this point.

Will it want to take over the world?

Yes.

Will it have Documentation?

I have plans for both written documentation and YouTube tutorials. I would hate myself if I didn't do this. Literally, how many times have I tried to write a plug-in in Ultra Hal and there was little to absolutely no help. Pretty frustrating. I wouldn't want anyone to go through that with Athena. Writing documentation should be one of the last things I need to do. Until Athena is totally finished, every thing will be in flux.

Although, I did consider making a short tutorial for Avatar creation today. I know that some people aren't interested in programming as I am and will lean towards the more aesthetic portions of Athena. A short tutorial, mainly showcasing the artistic possibilities, will help keep some people more interested in Athena. It is sad that I'm not able to create lifelike 3D Avatars. Creating skins for them would be attractive to the artistically inclined. I'm just not able to do this. I'm no Freddy. Maybe one day this will change.

Will can ask as many questions as Will wills, if Will is willing.

[Art]

Aaron,

Thanks for taking the time to answer the questions. I, for one, appreciate that.

It might be nice for the bot to ask for the user's name, the first time the program is run.

If you recall (or if you don't), one of UltraHal's plugin authors, vonsmith, wrote a routine for "ephemeral knowledge", meaning that this was information that was used in the current conversation but that info would have or might not have any bearing on future conversations so it was Not saved. "We're having a picnic today if it doesn't rain". Interesting for the conversation of "What are your plans for today?", but not worth keeping.

I've tossed around that Password idea for a decade I guess. I think it would be cool if your chatbot could keep a secret just between you and "her" (it). All other bots in the past were only too obliging to share whatever they knew.

Emotions - Well, there have been some fairly acceptable attempts to allow a simulated emotional condition for the chatbot. It seems that each emotion has a "weight factor". Once that emotion is triggered, the weight number is adjusted higher but only for a specific period of time. After say, a cooling off period, the number is reduced back to its original state and the emotional status returns to normal. Some bots, once angered, or insulted, often require an apology from the user in order to proceed with a normal personality (this weighted number reduced upon "realizing" an apology was obtained). Something to toy with and if implemented, I'm sure you'd mention such a weighted scale in your documentation so the user could modify if needed. Love seems to be a touchy topic and an emotional one in several chatbots so tread lightly. (you know how fragile hearts can be).

Everything sounds great so far and thanks again for your response.

Continued success.

[Snowman]

These two gems were in our newspaper yesterday and today.
Made me laugh.


https://goo.gl/photos/RnZD6kubjgRmJNsq6

https://goo.gl/photos/MnRSD9uYsAH7dGtL9

[Art]

Haha! That Wally really IS a pretty smart guy isn't he?!
Good ones!

[Snowman]

Well, It looks like they added another comic strip for today.
This lays out pretty much my whole ai design.... 

https://goo.gl/photos/6jwVLcYric7AQM8P8


... Although, I could let you know what I have done for the last week or two. As you already know, I've started working on assembling the Ai engine. So this is what I did for a few days before I discovered that my current database coding was causing a problem. It was too slow. So I've been trying a few things to speed it up. I know I can do it, but the code is a bit more complex than it used to be, therefore, it's taking me more time. This is nothing new, and its not a problem. It's just another day working on my block-o-wood Ai .

I put several thousand entries in my database and for some reason it slowed it down.. not acceptable. 
 

[Art]

Secret agenda!  Good stuff there!

[spydaz]

I have found that there are so many aspects in the aiengine that the concepts of ai can be useful when coding .

I mean . The decision tree concept ....

By creating a decision tree process which executes the code in mine i do
Parts of speech tag
Sentence identify
Then the type of sentence determines a decision which enables for complete sections of code to be ignored as they become redundant.....

The final decision at the end of the tree produces the response.

I have found thinking of it in this way helps to simplify the code ...

Now i think that the ai engine is the actual intelligence . As it makes the decisions even the plugins that are executed. Have to be evaluated . The complexity of decisions is knowing the parameters of the decision the more known parameters the higher the intelligence ie the making the most informed decision.

Maybe ?


Sent from my iPhone using Tapatalk