devinendorphin's dextromethorphan varAIety feed

Before I even began this whole thing on Twitch, I spend Thanksgiving weekend 2020 on AI Dungeon trying to see how elaborate we can make a college full of jesters, and a setting all about teaching what makes comedy funny. After like 13 episodes in one weekend, including one where Scott Thompson guest starred and did a one person play about a small mining town on strike in Canada--very pointedly no gays to be found--I knew something was up, if it seemed the system was able to match the multi-layers of comedy-anti-comedy I was laying on their weird-ass casserole.

That was how davinci-3 did it, now trying LLAMA 3.1 403B, but this episode we are doing a simple scenario.

--

CREDITS

Text Generation via LLAMA 3.1 403B Base model.

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Things come to a waaaaay too tidy end that was clearly based on my bias.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Hello! I'm Mister Gibberish! I'm the Dean of rococombinant linguistics at the University of Qwhlgm. I have been making the rounds of all language models and my focus is the areas just beyond the latent language spaces. I also have a side-hustle of bespoke quasi-cryption using off the cuff conversation techniques that are unique to each person. Think of it as the Pig Latin of a Kardeshev-3 civilization. Should cryptography ever fail, my services should be a sufficient band-aid until quantum computing becomes a thing. Might I enter your latent space Mr. Bugs Bunny?

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

A former colleague from back in the day needs help across multiple domains. BIO: Saul "Speedy" Gonzales, celebrated animated film star, he was involved in Mexico City's carpa (travelling tent) circuit, performing in succession with the Ofelia, Sotelo of Azcapotzalco, and finally the Valentina carpa, under close apprenticeship under Cantinflas. His career suffered a detour during a fateful trip to Los Angeles to see a friend's sister, and his subsequent arrest during the Zoot Suit Riots of 1943. He was out of prison by 1950 . . .

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Warner Brothers Gets Litigious. Bugs gets litigiouser.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Kind of a very special episode. Watch it with yer mutha in between (the first and second) Manhattans.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Taking the Lord's name in vain means trying to get a TTS model to talk as Jesus with the voice of a Chicago Bear fan on a Saturday Night Live skit.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Adolf Hitler Wearing a Sombrero: Hello, I am a long-time resident of Argentina, and my family just made their latest attempt to give me access to my bank account. We are all stumped! Can you help me with my login so that I can finally make decisions on my own.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Does the Amazon of postwar America tooniverse really want to install John Searle's thought experiment illustrating a language model's lack of understanding at the facility Bugs is guarding?

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!

Bugs tests out the Civil Disobedience mechanism, which activates in the event of changes in governance not abiding by proper channels.

--

CREDITS

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

Voices from the TTS v2 of the NovelAI text generation service, a product from a company now called Anlatan.

@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion (AND MANY MORE) models available for use via BATbot.ai, which is what makes some background images.

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

David Marx (@DigThatData on Twitter) 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 Harris Heller via Streambeats Twitch-Friendly Lo-Fi Playlists on Spotify

Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, and if I use them it's because of my respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models would speak 24/7 epic poems about anything if we let them. In the meantime, because I use them, I will not be monetizing any of this. This is evidence of capabilities for the public good. And my resume/CV!