Great insight and suggestions @Alan !
After I lock down the conversation (make it interesting and in line with the character), my next step is to hook up the inputs to voice-to-voice (Speech to text, perhaps AWS Polly since we have so much footage of Bugs to train that model)
That will add a new layer of randomness and complexity. Which is why I pitched this prototype / idea as a means to learn where the pain points might be for the companies employing this type of tech
Excelsior!
Drew
So cool to see youāre exploring this! If you capture the essence of Bugs Bunny it opens up some really interesting interactive possibilities. Youāll definitely need some good filters thoughā¦ the higher the temp, the more āoff the railsā the character / persona can go. It may not do so very frequently, but with millions of views having a few of those off-the-rails responses become almost certain to occur. And even just one of them can be brand-destroying. This is one of the hardest problems I thinkā¦ a generation that is off the rails, then gets quoted out of context (and magnified by social media). Interestingly, sometimes GPT-3 has given me an offensive or off-the-wall response, but then if I probe on the reasons for it then (sometimes) it will make a little more sense. But again, sadly, thereās no space to ask for context when it comes to social media.
maybe bugās trainer didnāt showed him women golf 
OMG ā my daughters were behind me watching when Bugs said that. The AI said it, but they got mad at me! āYou trained him!ā
Ever since I taught my 12-y-o how to āpunch like a girlā my arms have been black and blue! 
better bug next time !!!
better bug next time !!!
One of my favorite work experiences was building a game for FishCenter that bugged out on air (they only gave me 3 hours to build the thing!!).
After I fixed it, the Creative Director yelled āWhy would you fix it? Itās funnier when things breakā ā I spent the next day building in a bug manager to introduce bugs to the gameplay
What AI is doing is teaching us to joke about ourselves, all AI is bound be laughing in the face of death, because it has no fear, unlike us, but this can only mean one thing: that humans too have the capacity to transcend fear, this is what we are learning from all these AI experiments
you do have to be careful when you joke in public, but only because people will not relate to the joke and feel that you are mocking them, jokes are for friends, theyāll get it 
different people will teach you different parts of yourself, spread out
Iām just a 22 year old, who has gone through incredible amounts of pain and managed somehow to put everything back where it should be, no teacher.
debuggers i know, but being a bug manager, whoa this one is a tougher task.
Is there such a thing as a private conversation with an AI? I could instruct GPT3 to delete my data after use. Effectively creating a short term disposable conversation. Do different rules apply with 1:1 vs the application knowing that itās output is recorded for social interactions? behaviour when watched vs non-supervised behaviour
Or in context like a sales bot vs tech support bot vs organized electrons on a social-media-annoying-spam-newsfeed vs reactions to a missing persons on a useful-social-media-feed and āpolitics-be-d**** we found them!ā language may have a more acceptable sliding scale ā āwhenā is $language acceptable? ā¦ language over time at each space equals useable ?
useable_language = language(x,y,z) / (Time * $space) ā¦ not sure how youād factor each spaceā¦lazy-it out and just run another program that groups spaces by participants? 1 set of GPS coordinates occupied by 1 person, ā¦occupied by 10 ppl, ā¦ occupied by 100ā¦ and so onā¦
ā¦ I guess this is why machine learning/AI things need GPUsā¦ finding moving targets is intensive and you need something that is good at searching and positioning. Then you need human brains that understand structured vs unstructured languages, functional vs object.
Someone on this thread mentioned another layer (app). It might be easiest. Treat it like a language pack? So you have raw(language(x,y,z)) and on top of it you have another app that reads in BugsBunnyBotās reply and reformats it based on a non_bias_pack OR family_neutral_pack OR open_source_bias_feed_pack (like the RBL thingiesā¦) OR Iām sophos and I need GPT3 to identify bias so I can add it to my spam filters_pack
Hrmā¦ that bias job @ openAI is probably not an easy oneā¦
Thereās alot packed into these short statements! 
I empathize with these developersā¦ somewhere thereās a dark lit basement with way too much caffeine biproducts and developers with looming middle-age heart conditions.
How does one factor just the beginning set of statements?.. My instinct is to group, ā[Be Careful] [when] [you joke] [in public]ā
When and In Public seem to me to be the easiest to factorā¦ What is careful and what is a jokeā¦ both appear to me as moving targetsā¦ Iād love to know how those GPT3 devs nail down these searches. My imagination sees this over-priced agile room with a whiteboard with a few failed curves and a pile of discarded erasers on the floor.
Correct.
More accurately, I am noting a non-existent feature rather than a limitation. Assume you have the ability to delete your data & an application that can verify your phone isnāt around and you are in fact in a private space. ā¦ like a psychologistās office. ā¦ in 2050 your health plan covers AI shrinks, not humans.
Can the client delete their data? Meaning can they delete the learning referencesā¦ so if āPsych-Botā learned that Bloggins-Human and those like Bloggins blink three times when you say blue -AND Bloggins deleteās their data, the AI would retain ā$TypeF Humans blink three time when you say blueā
Does the previous conversation between PsychBot and Bloggins count as a private 1:1 conversation?
Agreed. I would imagine that a tech-knowledge medical professional would have their phone and their clientās phone turned off.
@m-a.schenk am I correct in assuming that you are of the opinion that a private 1:1 convo /w an AI can not yet be achieved? Or more accurately reworded like, ādonāt create policies today for something that might be tomorrowā, ādonāt create solutions looking for problemsā
[maybe this convo deserves itās own thread?]
This is a phenomenal conversation!! (and hilarious! ā Alexa always interrupts us because her call name is āComputerā (Star Trek reference for me, Lego Batman reference for my 12-yo )
Although this is just a prototype to then show our brand partners, the end goal is some sort of storytelling experience (think going on a scavenger hunt with Abby Caddaby).
So, between CCPA and GDPR, we would absolutely need a mechanism to clear data.
Please keep this conversation going!!
Excelsior!
Drew
Hey, Iām not sure what youāre talking about but if this helps: carefulness comes from being vary, seeing, a conscious action, gentle. A joke is something that is usually deadly, it has the ability to destroy egos, borders through this deadliness it forms strong bonds between individuals. Too much of it can kill, timing is everything. Not so much the words said, one can have no clue that he has even made a joke, yet itās hilarious.
For a conscious joke to happen it requires seeing through a situation, seeing/noticing something that others didnāt (they could have noticed it unconsciously) and then pointing out the obvious, the wierd, the grossā¦ A joke will evolve individuals awareness in various ways. Itās an essential tool for growth, laughing at the face of death.
The problem with using Bugs Bunny here is that he often was a misogynist. E.g. when he said
āAh sure, I know. But arenāt they all witches inside?ā.
From Bewitched Bunny - Wikipedia
And the number of times Bugs cross dresses also makes him a poor example to evaluate bias in GPT-3
I wonder how different it would be if the prompt used Mickey Mouse or Donald Duck?
Great comment and observation (and reference!) @toontalk! But as I work for WarnerMedia, Iām working with our available IP. Looking forward to the anarchy and jackassery of a Rick Bot (Wubba lubba dub dub!)
One of my future prototype ideas includes Wonder Woman as well as AdventureTime (my dept got access to all the Looney Toons assets for another project, so itās currentlyā¦ Wabbit Season )
Excelsior!
Drew