LLMs Just Got Outclassed: The Next 18 Months Are Wild!
Try Creao for free: https://creao.ai
Use this code for 30% discount when you go premium: RAEEHVKC
LLMs as we know them are already on their way out. In this video, I break down five breakthroughs that will redefine AI over the next 18 months: Diffusion LLMs (with Stanford’s Stefano Ermon), Power Attention for massive context, hidden/latent-space thinking and private chains of thought, Google’s Nested Learning for continual learning, and the most disruptive shift yet — Continuous Thought Machines (with Jaime Sevilla) as an early break from the Transformer itself.
If you want a fast, clear map of what replaces today’s Transformers — and why 2026 could be the turning point — this is your first look.
***************
Continues Thought Machine: https://youtu.be/DtePicx_kFY?si=otNIJriyoFElrp-k
How Diffusion Language Models work(Julia Turc): youtu.be/bmr718eZYGU?si=uLHzbGfu856O8YjJ
Diffusion Language Model (Mercury): https://www.inceptionlabs.ai/
Nested Learning: https://research.google/blog/introducing-nested-learning-a-new-ml-paradigm-for-continual-learning/
OpenAI VP of research interview on The Mad Podcast: https://youtu.be/RqWIvvv3SnQ?si=xXs0dZkUWvyvRgCP
OpenAI new research direction live: https://youtu.be/ngDCxlZcecw?si=M3P2vsqgvob_Xmj-
Attention is all you need: https://arxiv.org/abs/1706.03762
Continues Thought Machine: https://arxiv.org/abs/2505.05522
Power Attention: https://arxiv.org/abs/2507.04239
****************
00:00 Intro
00:32 First Technology
07:01 Second Technology
16:47 Third Technology
20:56 Fourth Technology
23:57 Fifth Technology + Future AI Trends
***************
All materials in these videos are used for educational purposes and fall within the guidelines of fair use. No copyright infringement is intended. If you are or represent the copyright owner of materials used in this video and have a problem with the use of said material, please contact me via my email in the “about” page on my channel.
**************
#AI #LLM #DiffusionModels #Transformers #Attention #LongContext #ContinualLearning #DeepMind #OpenAI #machinelearning
source
