If you would like to test out a similar (though less powerful) text-to-music model, try out Riffusion here: https://
riffusion.com – I have shared several videos of this platform to my Instagram and TikTok.
@alliekmiller
-
Test Riffusion: A Less Powerful Text-to-Music Model
By
–
-
Google’s Paper Addresses Cultural Concerns in AI Music Models
By
–
Google's paper also addresses concerns around underrepresented cultures as well as cultural appropriation and calls for more research/collab before any model is released for public use. The paper is best suited for an intermediate AI folks with a basic understanding of music.
-
AI-Created Short Film Blends ChatGPT Script with David Turk’s Animation
By
–
My insanely talented friend @thedavidturk created this short with AI. ChatGPT created the voiceover script and provided a list of camera angles, lens, and focal length based on Christopher Nolan movies. Art and animation done by David. Watch it here:
-
GPT-4 Capabilities: Data Visualization Joke About Future AI
By
–
And for my data storytelling purists out there, this is just for scale comparison. I do not actually think GPT-4 will have the ability to eat hamburgers or run marathons. But GPT-5, however…
-
GPT-4’s Rumored 571x Parameter Increase Compared to GPT-3
By
–
This thread is for entertainment purposes only and is based on the rumored 571x gain in parameters for GPT-4 (100T) from GPT-3 (175B). As a point of comparison, the leap from GPT-2 to GPT-3 param count was only 116x. ChatGPT is finetuned from a model in the GPT-3.5 series.
-
Correcting misconceptions about GPT model training data amounts
By
–
Also note that other threads have incorrectly stated that 100T is the amount of the data the models were trained on. According to Hyro AI, GPT-3 was trained on 570GB of data. And according to Sigmoid, GPT-2 was trained on 40GB. I have not seen a rumored amount of data for GPT-4.
-
AI technological leap compared to stone tools to iPhone
By
–
That’s how big of a leap this technology is. So when you see those of us who have worked in AI for the last decade describing these monumental shifts in research, compute, and capabilities, just know this isn’t AirPods to AirPods Pro. This is etching in stone to iPhone.
-
GPT-3 vs GPT-4 Parameter Count Calorie Comparison
By
–
You are GPT-3 parameter count and your friend is GPT-4’s. You eat one Big Mac. They eat the daily recommended calorie amount for five and a half months.
-
GPT-3 vs GPT-4: Comparing Parameter Counts Through Marathon Distances
By
–
You are GPT-3 parameter count and your friend is GPT-4’s. You walk 1 mile. Your friend, Eliud Kipchoge, completes almost 22 full marathons.
-
GPT-3 vs GPT-4: Comparing Knowledge and Parameter Scales
By
–
You are GPT-3 parameter count and your friend is GPT-4’s. You know everyone’s name in Cape Verde. Your friend knows every single person’s name in California…and everyone in the other 49 states as well.