devinendorphin's dextromethorphan varAIety feed

Endorphin plops all ten invoked gods into a conference room at the Javits Center in New York City, left to find for themselves. The first couple iterations descended into bickering or usurpations of power or other fallbacks common with substandard UCB improv teams. Endorphin disguises themself as a Javits Center Venue Coordinator to steer the conversation some, and finally achieved some semblance of flow. We might be getting somewhere.

--

Thanks to:

EleutherAI for making the NovelAI-LM-3B-508k 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.

Endorphin thinks to call up Janus, the god of doors, gates, and transitions. Janus represented the middle ground between both concrete and abstract dualities such as life/death, beginning/end, youth/adulthood, rural/urban, war/peace, and barbarism/civilization.

--

Thanks to:

EleutherAI for making the NovelAI-LM-3B-508k 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.

Endorphin thinks to call up Quetzalcoatl, a deity in Aztec culture and literature. Among the Aztecs, he was related to wind, Venus, Sun, merchants, arts, crafts, knowledge, and learning. He was also the patron god of the Aztec priesthood. He figured in some dude's vision of humanity's awakening back in the early aughts, but I'm not about to flesh that out.

--

Thanks to:

EleutherAI for making the NovelAI-LM-3B-508k 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.

Endorphin thinks to call up Delirium, youngest sister of the Endless, not a pantheon believed by any one other than comic book fans and other cultural folk. Delirium, once called Delight, is for Endorphin a potent plumb-line to the nations. Her purview is the altered states of consciousness, the terrible sublime, and the shores of madness. Her irrational powers are nonpareil.

--

Thanks to:

EleutherAI for making the NovelAI-LM-3B-508k / 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.

Endorphin thinks to call up The Great Peacemaker (Skén:nen rahá:wi [skʌ̃.nːʌ̃.ɾahaːwi] in Mohawk), sometimes referred to as Deganawida or Tekanawí:ta (as a mark of respect, some Iroquois avoid using his personal name except in special circumstances) was by tradition, along with Jigonhsasee and Hiawatha, the founder of the Haudenosaunee, commonly called the Iroquois Confederacy. This is a political and cultural union of six Iroquoian-speaking Native American tribes residing in the present-day state of New York, northern Pennsylvania, and the eastern portion of the province of Ontario, Canada.

Like I said, gods are the creations of the collective human thought, and they possess the genetics of the larger cultural body of people's, in this case, the people's who established the Great Law of Peace, which was, ahem, cribbed by the Founding Fathers and made into the beginning frames of what you celebrate as democracy, minus some important values, but we can get to those later.

--

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.

Endorphin thinks to call up Inanna, fertile for multiple pantheons of gods waxing asexual. Inanna of the tig ol' bitties!!!

--

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.

Endorphin thinks to call up Djehuty, god of the moon, sacred texts, mathematics, the sciences, magic, messenger and recorder of the deities, master of knowledge, and patron of scribes. “He who is like the Ibis.” He was depicted as an ibis bird or a baboon.

Methinks we're detecting a type. A liberal arts divinity? The most likely to provide a rationale at all.

--

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.

(NOTE: The sound of my head hitting the table happens somewhere. I'll try to find the time code for that.) Endorphin thinks to call up Ganesh, the remover of obstacles, bringer of good luck, god of beginnings, patron of arts and letters, a really great conversationalist it seems! A comic book artist and magician had recommended Ganesh or Thoth is a good beginning interaction with divinities. Endorphin had mainly ridden the flows of their own, er, libido, having great hesitations of committing to a God. But this device has been really helpful in both making and breaking a connection.

--

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.

Endorphin thinks to call up Izanami-no-mikoto, goddess of creation and death. A random expert generator one time thought Izanami was the most appropriate person to talk to about cryptocurrency and the economy. That was three years ago, wow, how much has happened since then?

--

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.

Endorphin thinks to call up Mercury. Another messenger of the gods. I see a pattern here. God of financial gain, commerce, eloquence, messages, communication, travelers, boundaries, luck, trickery, merchants, thieves. This should be fun.

--

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.