Runway’s NEW AI Video Model is INSANE

Discover the power of Runway Gen-4, the groundbreaking new image-to-video AI model that takes creativity to the next level! In this video, I dive deep into what makes Gen-4 a major leap forward in AI filmmaking, creative control, and motion generation. In the video I will also compare Runway Gen-4 against Gen-3 and Kling 1.6. Kling AI is the state of the art AI video model and Runway Gen-4 is a true challenger for Kling 1.6. With Runway Gen-4, you can now control scenes, single or multiple subjects, camera movement, and how all these elements interact—unlocking cinematic storytelling with AI like never before. The model creates smooth, realistic motion, captures emotion in characters, and offers a sense of natural flow rarely seen in AI-generated video. I’ll also break down the latest Gen-4 prompting techniques, based on the official guide, so you can start generating high-quality AI videos right away.

THIS is why large language models can understand the world

5 years ago, nobody would have guessed that scaling up LLMs would as successful as they are. This belief, in part, was due to the fact that all known statistical learning theory predicted that massively oversized models should overfit, and hence perform worse than smaller models. Yet the undeniable fact is that modern LLMs do possess models of the world that allow them to generalize beyond their training data. Why do larger models generalize better than smaller models? Why does training a model to predict internet text cause it to develop world models? Come deep dive into the inner working of neural network training to understand why scaling LLMs works so damn well.