1. Partial client side execution of the models, then main model execution in cloud. (Example: text encoder for Stable Diffusion runs local, UNet runs cloud)
2. Local LoRAs for “dynamic ML”
3. WebGPU will be new standard to unlock models in the web
Even though the article had some good calculations and overview, I am not sure word-for-word is how I would describe its relationship to the OP.
For those that don’t know, this website and lifestyle were actually heavily inspired by CS/Machine Learning work done by Ken Stanley and Joel Lehman.
They co-authored a book, Why Greatness Cannot be Planned, about the philosophy and results behind an algorithm they developed for evolutionary computation with no explicit objective other than finding new artifacts: Novelty Search. You can see a review of the book here: https://medium.com/@John_Saunders/what-ive-been-reading-why-...
As I understand, the author of this site took the work quite literally!
If you’re into the intersection of CS and philosophical topics, I’d highly recommend reading the book.
Some predictions in the article:
1. Partial client side execution of the models, then main model execution in cloud. (Example: text encoder for Stable Diffusion runs local, UNet runs cloud)
2. Local LoRAs for “dynamic ML”
3. WebGPU will be new standard to unlock models in the web
Even though the article had some good calculations and overview, I am not sure word-for-word is how I would describe its relationship to the OP.