Search archive

I drop projects a lot and having too much scope can kill tons of projects. these of course are all just ideas. programming an entire model rigging system is it's own project. let alone hooking it up to an AI.

I almost definitely will Gent Don't go and pull a no man's sky on us

but i think it would be fun to be able to feed it verbs, and it could output model rigs based on it's current feeling and verb values

The first iteration of the AI will have rig support for it's own puppet. So it'll be like a little cortona, since it's trained off my exes spea=ech it'll probably just end up doing thing to spite me. which should be fun to watch. learning that I have a type lmao

Actually! funny you mention puppet pals

it would be quite some time from now as I am still working on improving training times and quality from the algorithm. Right now it is very fast, although it could easily be much much faster. for instance the activation function could be a unique one for this sort of data. since it's highly specific to text and not gen

holy shit Phijkchu_Pikachu @Tinkerer_Red here is hte justin stuff btw

so you could start in the den of devils campaign and end up randomly in the silvermines mountain.

really the only problem is the AI will not really remember what the campaign is actually about

if you're feeling frisky for a weird campaign.

or virtual deadbones

exactly

convert the audio into a spectrogram, then have the ai do it's own smoothing filter. to train it you just have another ai which knows humans from robots, when it guesses the robot is a human 50% of the time then you have a good enough voice

yup Garbage So like mixing splicing of old but with much more samples and assisted by an AI to merge them together to make it sound natural?

It's the same thing siri and alexa does

basically just take the single phoname, find it 100 times. stretch them into place and paste em all over each other. it'll sound like shit but the AI will smooth it properly (hopefully)

It's not hard to extract and average phonetic from audio

I actually do intend to work on a voice module for the AI, but it wouldnt be truly synthetic, more like AI assisted smoothing of the phonetic audio clips. Garbage Train an AI off of videos only featuring rob talking, i;e some lords episodes and pokemon nuzlockes to make an AI voice that kinda sounds like rob KappaHD /s

Afterwards I'll be training it on a few months of messages between 2 replika AIs to givwe it a quick kick start, then training it on real human data between me and my exes since that is likely the largest dataset i have between 2 people talking. afterwards I will have a trained agent which can be applied to many more s

So technically speaking i would have more neurons, although the AI would be much much faster

normally an auto encoder uses 2-5 values per word. If I can compress this down to just one and the encoder works properly then I can cut down the training time and calculation time by Nth degrees

so now i have 122188 words all with a single value. ie: yogurt, 0.7066295094612451

Then used an adjusted 1d boids algorithm to have every word move closer to similar words. repeated this until no word moved from a regular position in the list for 10 iterations straight.

I've chosen not to use an "auto" encoder, and instead use an assisted auto encoder. So I spent about 8 months crawling the web for a wide veriety of words. then spent another 6 months crawling every synonym and antonym for all of those words, then the syn and ant of all those... etc. Spooky Phijkchu So what's the angle

ah yes, the names only make sense

love small communities anyways

sick

i'm home Phijkchu_Pikachu most of the upper level academics here are engineers, with me being a mathematical physics major. We have a few people who know some cs stuff though

NEAT is indeed the algorithm im using lol

learned it all by my self Phijkchu_Pikachu You a cs major I take it?

since i'm working on my portfolio, i need to express that i fully understand the logic. so everything i'm using is written by me. no libraries needed. Also helps massively with optimizations for training. Spooky Phijkchu do you have access to some good libraries for language processing?

Anyways I'm currently working on my portfolio, training an AI on a non standard language attempting to produce similar results to Replika with far less required neurons and better memory. So obviously if this works out, then i could apply this to all of the urealms campaigns and see what comes out from it.

ayy

Anyways training it on speech first, then developing it for a transcript of urealms live shows I would be able to get a much more refined AI with a few less neurons required

link for the lazy: https://play.aidungeon.io

Well AI Dungeon is the idea, although they trained that on a LOT of unrelated datasets.

i seen that very impressive and several people have messaged me so far about getting the content. So I'd be happy to send them your way Spooky Phijkchu but really, I love finding other archivists we have 3 folks here, and we put together the https://rawb.art site (edited)

I've been working with AI recently, and by sheer coincidence, all this happened recently and people reached out to me on a dead forum. happened, by chance to see an email. which lead me to this. So I'm thinking about working on a new AI to be able to DM an entire campaign

Anyways

lol

i heard, Phijkchu_Pikachu reached out to me

lol

what an interesting last few days it's been for me

joined the server.