[yotamarker]

the persona the AGI uses also plays a roll
for example if she is telling a story to women she will focus more on the financial elements of the story
and tell it from the POV of a woman.

[yotamarker]

story time rate :

time minimized : summary exp : and then it was morning she returned
time real = scene time exp: he walked over to the door reached for his key and unlocked it
extended time : description : she grabed the kettle with her big robotic hands with the greatest of ease
only using her one working hand as it shook...

[yotamarker]

story epic mode : used for high value characters forth wall is broken done in scene time.
uses character markers to interact with the audience

dramatic mode : also focal point changes per character. uses turns, to switch characters

[yotamarker]

the story teller can only get new data from the audience
is that why we don't talk to chairs ?

[Art]

Perhaps we could, but then they would be called "Chairacters"!

[jlsilicon - Robotics AI]

Interesting ideas presented earlier in this discussion.
- Sequential Situational Memory
- Referential
- Recalling Memories

Has anybody tried these AI Rules in testing them ?

[yotamarker]

I'm on the notebook stage takes time doing this alone also
the story algorithm must coexist with the rest of the A.I capabilities

[yotamarker]

how would you define a filler episode ?

[yotamarker]

would it be correct to say fillers are chronologically backwards ?
on the other hand the past repeats itself so under that logic everything is a filler

[yotamarker]

I am begining to see some pattern between physical maps relations to chronological sensory logs
or goals to expressions

[yotamarker]

there is no story without a map
the map is the story

[TR]

I registered to be able to make a comment on this...

I quite like the saying, "People are stories that tell themselves".

Scriptwriting is creating a model of a fictional world, likely based around a fictional character.  This is just what storytelling is.  Modelling ability is critical for an AGI, predicting what is likely, checking this against feedback, updating the model.

The generalising side is taking this ability to model the (real) world, and recycling it to model a fictional world.  That's a very human thing to do, and, if an AGI is going to interact with human society an AGI must be able to do this.

Now, I can hear all those people complaining, "I don't want my AI to be able to lie!  If she can lie how can I trust what she tells me?".  The answer to that is "Consequences".  Unless those interacting with the AI understand and agree that the current context is a storytelling one, people will get upset.  Past a certain point, upset people are really bad news for an AI.  This feedback will tell the AI that 'storytelling' had better be the agreed context before embarking on it.

(Yes, I know, I switched from 'AGI' to 'AI', but if you can find anyone in the general population who can tell you what 'AGI' means, I'll be pleasantly surprised. )

Now, if I was really evil I'd start talking about meta-modelling, maybe even meta-meta-modelling, but, I'm not evil.  Honest

[HS]

I think modeling is our method for assessing what is likely, and storytelling is our method for changing what is likely. It’s somewhat of a specialty, we learn to alter the future before we learn to walk. But as we learn to read, the level of compression gets even crazier. The sheer expansion of script to shape… It’s literally words to worlds. Generating environments from text (symbols) would be the “Turing” test I’d like to see. A.I script reader. 

[spydaz]

Hiya Been a longtime posting ; but been working hard on various aspect of AI and focusing on coding the new programming languge and tools for creating converational AI and Knowledge learning from conversation and text etc.. lol.

After reading some posts: Its very interesting : story generation ; script generation ;Parts of speech tagging etc (code generation)<<<<Very important as the code generation / compiler / interpretor pattern <<<<< provides understanding on HOW? a domain specific language can be implemented ;

i have been looking at the possibility of generation of text ; scriptwriting ; Storytelling. I have had some minor sucesses and ideas as well as programming failures ;

I belive the concept is sound, and yet when generating the first set of sentences based upon Sentence structure i realised as the computer did not understand the relationships between the components of the generated sentences whilst gramatically correct were giberish.
With a more supervised approach ; phrase based? yes with such pre created phrases ; with HEADINGS such as "intorductin" (once upon a time, ....etc) a nice story could be generated by allowing for some random selection for NOUN Object such as names colors etc. ccreating simular yet differnt stories. leading to the understanding that preprogramed phrases works and yet left little scope for actual story generation , YES , Supervised works but is limited by the source phrases for each section of the story such as ENDINGS etc. (they lived happily ever after)
NOW, In understanding that storys regarding knowledge known about a THING? ie what is a cat? , based on stored data regarding a cat and its relations based on wordnet/verbnet/concept open minds and other such languge modeling; a dictionary response based on such collected data can be framed with such pre programed phrase structrues based on thier capture/ learning patterns, this generation allows for FORMAL sentences to be genearted about such a  thing.
AGAIN;  Regarding Conversational data collected ; this leads to scenario based sentence generation , this style of sentence generation has SOME preprogramed phrase structures also based on TIME/LOCATION/WHO/WHAT/WHY/WHEN. this temporal data ie: Short term memory has its own domain specific collected data and knowledge; sentence structure can be generated based on the collected grammar from sentences learned; ie: as we the human speaks we are unaware of the noun phrase and verb phrase relationship . the subject object / predicate... but in speach the AI can collect such phrases and store thier gramatical structures for reuse in sentence generation. this loosly based semi unsupervised/supervised learning also has pattern associtead and domain specific knwledge to represent;
In Combination of techniques a formal personality and an informal persoanlity can be produced (speech pattern based) . yes from the random sentence generator, to pattern based formal generator(domain specfic) to informal(user gramar based)(domain specific(temporal)).
this combination technique for Sentence generation Can use both RANDOM and FOCUSED Sentence generation to produce a script based on Goals headings and domain specific knowledge and grammar choice and selelction can be improved by neural network for comparisions against known human responses for the same domain specifi knowledge. the learning model would no use the output of the script generating algorithim for error correction or focused NLP of the final outputs expectations and human sounding response;

AGAIN;
This is only (MY EXPERIENCE) my personal insight!