Support us! https://www.patreon.com/mlst.
If you don’t like the background music, we published a version with it all removed here — https://anchor.fm/machinelearningstreettalk/episodes/Music-R…on-e1sf1l7
Continue reading “Prof. DAVID CHALMERS — Consciousness in LLMs [Special Edition]” »
The Future is Upon Us.
DreamFusion: https://bit.ly/3UQWIjh.
Nvidia Get3D: https://bit.ly/3dU9KMa.
Dream Textures A.I: Seamless Texture Creator.
Explore Sketch to 3D [Monster Mash]: https://youtu.be/YLGWsMfAc50
See Nvidia Nerf: https://youtu.be/Sp03EJCTrTI
Join Weekly Newsletter: https://bit.ly/3lpfvSm.
Find BLENDER Addons: https://bit.ly/3jbu8s7
Learn to Animate in Blender: https://bit.ly/3A1NWac.
See FiberShop — Realtime Hair Tool: https://tinyurl.com/2hd2t5v.
GET Character Creator 4 — https://bit.ly/3b16Wcw.
GET AXYZ ANIMA: https://bit.ly/2GyXz73
GET ICLONE 8 — https://bit.ly/38QDfbb.
Check Out Unity3D Bundles: https://bit.ly/384jRuy.
████████████████████████████
DISCORD: https://discord.gg/G2kmTjUFGm.
Twitter: https://bit.ly/3a0tADG
Music Platform: https://tinyurl.com/v7r8tc6j.
Patreon: https://www.patreon.com/asknk.
████████████████████████████
GET HEADSHOT CC: https://bit.ly/2XpspUw.
GET SKIN GEN: https://bit.ly/2L8m3G2
ICLONE UNREAL LIVE LINK: https://bit.ly/3hXBD3N
GET ACTORCORE: https://bit.ly/3adV9XK
Continue reading “Dream Fusion A.I — Everyone Can Now Easily Make 3D Art With Text!” »
On Thursday, a pair of tech hobbyists released Riffusion, an AI model that generates music from text prompts by creating a visual representation of sound and converting it to audio for playback. It uses a fine-tuned version of the Stable Diffusion 1.5 image synthesis model, applying visual latent diffusion to sound processing in a novel way.
Since a sonogram is a type of picture, Stable Diffusion can process it. Forsgren and Martiros trained a custom Stable Diffusion model with example sonograms linked to descriptions of the sounds or musical genres they represented. With that knowledge, Riffusion can generate new music on the fly based on text prompts that describe the type of music or sound you want to hear, such as “jazz,” “rock,” or even typing on a keyboard.
The Expanse is one of the seminal sci-fi shows of the past decade. Set centuries in the future when humans have colonized the solar system, it’s been called one of the most scientifically accurate sci-fi shows of all time. But just how much does this hold up to scrutiny?
Join this channel to get access to perks:
https://www.youtube.com/channel/UCF5F2zbc6NhJVyEiZGNyePQ/join.
My avatars were cartoonishly pornified, while my male colleagues got to be astronauts, explorers, and inventors.
When I tried the new viral AI avatar app Lensa, I was hoping to get results similar to some of my colleagues at MIT Technology Review. The digital retouching app was first launched in 2018 but has recently become wildly popular thanks to the addition of Magic Avatars, an AI-powered feature which generates digital portraits of people based on their selfies.
But while Lensa generated realistic yet flattering avatars for them—think astronauts, fierce warriors, and cool cover photos for electronic music albums— I got tons of nudes.
Musicians, we have some bad news. AI-powered music generators are here — and it looks like they’re gunning for a strong position in the content-creation industry.
“From streamers to filmmakers to app builders,” claims music generating app Mubert AI, which can transform limited text inputs into a believable-sounding composition, “we’ve made it easier than ever for content creators of all kinds to license custom, high-quality, royalty-free music.”
Of course, computer-generated music has been around for quite some time, making use of various forms of artificial intelligence to come up with results that can sound equally manmade and alien.
How could we one day travel between the stars with real physics? Perhaps the greatest challenge to interstellar flight is energetics — it takes vast amounts of energy to accelerate even small ships to 20% the speed of light. But what if we could steal that energy from where? Perhaps even a black hole. Enter the “halo drive”, a video by Prof David Kipping based on his new peer-reviewed research paper on the subject.
This video is based on research conducted at the Cool Worlds Lab at Columbia University, New York. You can now support our research program directly here: https://www.coolworldslab.com/support.
The Kardashev Scale has become a standardized way of classifying (hypothetical) advanced civilizations. The lowest rank, Type 1, is still way ahead of us — but by how much? When will we achieve Type 1 status and exactly how could we plausibly do so? In this video, we go through some estimates of when humanity might become Type 1, and in particular what kind of energy sources we could harness to achieve this feat.
You can now support our research program and the Cool Worlds Lab at Columbia University: https://www.coolworldslab.com/support.
Continue reading “Becoming a Kardashev Type I Civilization” »
