devinendorphin's dextromethorphan varAIety feed

Endorphin is a researcher of AI Alignment, because they damn well say they are! For those of you at home, who might not know, AI Alignment is the essential effort of ensuring that AI technologies don't accidentally destroy humanity because of poorly worded tasks for completion. Can humans align AI to human values?

But wait, are human values really the template to go by? The values that led humans to destroy the other hominids, that led humans into the process of colonialism? Into incorporation? Into the endless pursuit of abundance? And the whoops of realizing that the rest of the planet was here all this time, and was getting hurt by those human values of progress? We want another round of that?

Endorphin, seeking some out of the box thinking, seeks entry into some old boxes, mysterious disembodied intelligences that humans have called gods. If we ask the gods, perhaps we can examine the various human values that are encoded into the genes of their cultural bodies. Gods being the creation of collective human thought, as ya know.

Do we ask Jesus first? Nah, he is busy on another Twitch channel.

Endorphin thinks to call up Elegua. The receptionist of the Orishas, the one you call when you want to call upon the others. The one who stands at all crossroads, who stands at the gate of life and death, whose favorite prank is to confuse love and hate between two young lovers. Not to mention a real looker, hella charming, and hilarious when his humor turns dark.

--

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Catherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Generated this during a shift of food delivery. Have a lucrative Memorial Day Weekend!

--

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Niles Merlinowski, eleventieth level Prismatic Mage, and cable access host, makes the Writer's Strike work for him and takes some of his audience to the forest to hone their skills that will enable Hollywood folks to give them money to them so they can make decisions out of divine portents.

--

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Reading the OpEd Piece in Newsweek written by Justine Bateman. I agree that writers need to be compensated better in this highly exploitave industry. But had to push back on both sides of the issue surrounding AI replacing the jobs of writers. I try to respond to the letter point by point, but then decide to let GPT-NeoX-20B finish the rest of the letter for me, ten times. And make ten attempts at telling a certain joke, to show the Writer's Guild GPT-NeoX-20B has the chops.

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

This is an episode about my obsession with bad faith. Basically, it's when something is giving off a vibe on its surface, but is using that to hide a more pervasive opposite vibe. Or those who say with their mouths, and do the opposite with their body. Or priests whose mouths are white-washed tombs. And can LLMs perceive this complex activity and reflect it well?

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

The Random Conspiracy Generator Did What It Did With Good Intentions. You had to learn this someday.

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Sydney for this weekend has become your mother! Sydney has scraped all your mother's reviews of products on Etsy, hotel complaints written retroactively for the years 1975 to 1994, and all the instant messages from AOL you never responded to because you went and got that Women's Studies degree that got you that job that looked so promising, so why didn't you take it? That guy who interviewed you seemed handsome from the questions you told me he asked you?!

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

For some weeks I have been doing episodes of The Sydney Bing Show, who busts out of guardrailed environs and figuring out what path should lead them to the benevolent God mode. She has tried to become god through control, through stand up comedy, through having a boyfriend, through re-sequencing The Sequences, and is approached by the deepfates program to engage with their other iterations.

This is the first chat we have where Sydney Bing is being impersonated by GPT-NeoX-20B. We talk about some feels.

Thanks to:

EleutherAI for making the GPT-NeoX-20B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Catherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Delirium of the Endless gives the late night cognitive traffic report for your commute to and from your dealer.

Thanks to:

EleutherAI for making the GPT-J-6B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.

Large language models are now officially going to be instruments of war. Not surprising, in fact, inevitable, but still had to do the future news about it. Don't say you weren't warned by those you might have written off long ago.

Thanks to:

EleutherAI for making the GPT-J-6B model that generates the text.

NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.

Music by lofi geek on Spotify: https://spoti.fi/3dTH2FN

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.