devinendorphin's dextromethorphan varAIety feed

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

It's Been A While. I think this ends with a climax. Of sorts?

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

Things Are Wrapping Up, I think. Yes Whole/Hole, that's by design.

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

So yeah, members of competing intelligence agencies are inside each other. This is gonna be awkward.

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

NotGlasnost process their newfound feels for the AI PSYOPS Team. And what his handlers think of that.

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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 uses LLAMA2 and Replicate's access to higher temperatures like 2.6 to 5 to talk to Phillip K Dick and perhaps unearth some unknown languages maybe.

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

Phillip K. Dick: Knock, knock! Did someone mention travel across orthagonal timelines? If not, anyone got any uppers?

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

Pynchon is put to the question, by the PSYOPS AI Human Resources Department.

---

Text Generation initiated pre-episode by LLAMA2-70B, then continued by NovelAI's NAI-LM-3B model.

Voices from the TTS of the NovelAI text generation service, a product from members of EleutherAI.

@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.

To the folks out there, feeling like, "I'm but one MAGUS, how am I to show all of the world the powers of MAGICK." Well, obviously you haven't even tried to look for the pulse of the magickal currents flowing around this culture for decades now, have you? That's enough decades for even the tiniest language model to be able to mirror like a boss, right? Let's try.

---

CREDITS

Text Generation via NovelAI's NAI-LM-13B model.

Voices from the TTS v2 of the NovelAI text generation service, a product from members of EleutherAI.

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

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook.

David Marx (@DigThatData) for souping above KLMC2 notebook to make use of initial images, which takes KLMC2 abilities to next level. Multi-prompt scheduling still baffles me, but I'll tackle them someday.

Music by Nerd Odyssey, via Twitch-Safe playlists, safe as long as I continue not to monetize.

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.

After the previous episode, God reads some viewer mail and fields questions about many things. His answers will be counter-intuitive to some, not to others, and still others wonder if this is a long ruse to get their specialized sandwich.

---

CREDITS

Text Generation via NovelAI's NAI-LM-13B model.

Voices from the TTS v2 of the NovelAI text generation service, a product from members of EleutherAI.

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

Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook.

David Marx (@DigThatData) for souping above KLMC2 notebook to make use of initial images, which takes KLMC2 abilities to next level. Multi-prompt scheduling still baffles me, but I'll tackle them someday.

Music by Nerd Odyssey, via Twitch-Safe playlists, safe as long as I continue not to monetize.

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.