What if you could make AI language models smarter by reusing the same layers over and over? Researchers from KAIST, KRAFTON, and UC Berkeley present LoopMDM（Looped Diffusion Language Models）. They selectively loop early-middle transformer layers in masked diffusion models—no
INNOVATION
-
Cursor’s frontier model with 100x fewer resources than Google
By
–
it is wild that Cursor trained a model closer to the frontier than Google with 100x fewer people and (guessing) ~100x less compute i am surprised this was even possible. also praying for the Gemini comeback ofc
-
Stop pitching hardware startups coupled with models
By
–
Please stop pitching me hardware startups that are tightly coupled with models No, printing model architectures on hardware isn't smart, it's a waste of PCBs and memory GTX 1080s from 10 years ago could run today's models, but a model on a PCB today won't be used in 10 years
-
Google Gemini 3 Deep Think Advances Scientific Discovery
By
–
How Google Is Pushing Scientific Discovery with Gemini 3 Deep Think
— Ronald van Loon (@Ronald_vanLoon) 28 mai 2026
by @GoogleDeepMind
#ArtificialIntelligence #MachineLearning #ML pic.twitter.com/zrkVpkdu3kHow Google Is Pushing Scientific Discovery with Gemini 3 Deep Think
by @GoogleDeepMind #ArtificialIntelligence #MachineLearning #ML -
OpenAI for self-improving tax agents: A revolutionary approach to tax administration.
By
–
OpenAI for self-improving tax agents:
-
Block-by-Block Neural Network Training Framework
By
–
ニューラルネットワークをブロックごとに学習する枠組みを開発
— Sakana AI (@SakanaAILabs) 27 mai 2026
ブログ: https://t.co/45Xvzl1T1k
ニューラルネットワークの学習は通常、ネットワーク全体を一度に扱う必要があり、深いモデルほど多くのメモリを必要とします。このメモリ消費は、近年のAIモデルの大規模化を支える上で大きな制約と… https://t.co/DhnviMIgPdDeveloping a Framework for Learning Neural Networks Block by Block Blog: http://
pub.sakana.ai/diffusionblocks Neural network training typically requires handling the entire network at once, and deeper models demand even more memory. This memory consumption has become a major constraint in -
WordPress categories covering AI topics
By
–
Web designers after reading this: https://t.co/yONuEtjT8L pic.twitter.com/p3y16ldruL
— Charly Wargnier (@DataChaz) 27 mai 2026Web designers after reading this:
-
Managed Deep Agents for Long Horizon Deployment
By
–
Managed deep agents is the easiest way to build and deploy long horizon agents Private preview, dm me if you want access
-
5-second video generation in 4.2s on single Blackwell GPU open-sourced
By
–
You should read this thread.
— NVIDIA AI (@NVIDIAAI) 27 mai 2026
It used to take about 25 seconds to generate a 5-second video on 8 Blackwell GPUs. The legends at @haoailab brought that down to just 4.2 seconds on a single Blackwell GPU… and then open sourced the tech behind it. https://t.co/egQnhx0N1eYou should read this thread. It used to take about 25 seconds to generate a 5-second video on 8 Blackwell GPUs. The legends at @haoailab brought that down to just 4.2 seconds on a single Blackwell GPU… and then open sourced the tech behind it.
-
Fleet Agents Now Execute Code for General Tasks
By
–
Fleet agents now come with a computer! They can write and execute code, which is helpful for general purpose tasks beyond coding