🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

BASED ✌️ turns 1! One year since its launch at NeurIPS 2023 — and it's helped shape the new wave of efficient LMs. ⚡️ Fastest linear attention kernels 🧠 405B models trained on 16 GPUs 💥 Inspired Mamba-v2, RWKVs, MiniMax Checkout our retrospective below!

best application of robotics

The Great American AI Race. I wrote something about how we need a holistic AI effort from academia, industry, and the US government to have the best shot at a freer, better educated, and healthier world in AI. I’m a mega bull on the US and open source AI. Maybe we’re cooking

So excited to be speaking at #ted2025 this year! I’ll be talking about the intersection of AI and biology 🧬

Super excited to share Chipmunk 🐿️- training-free acceleration of diffusion transformers (video, image generation) with dynamic attention & MLP sparsity! Led by Austin Silveria, soham - 3.7x faster video gen, 1.6x faster image gen. Kernels written in TK ⚡️🐱 1/

I'm at #ICLR2025 this week to present our work on🔬high-precision algorithm learning🔬with Transformers! Stop by our poster session Thursday afternoon! 🔗arxiv.org/abs/2503.12295 With Jess Grogan, Owen Dugan , Ashish Rao, Simran Arora , Atri Rudra, and hazyresearch!

🧵 1/8 AI is everywhere—from massive cloud systems to your smartphone. But building fast, smart models for edge devices is still a major challenge. Most small models rely on Transformers... until now. Introducing Hyena Edge: our new efficient and high-quality multi-hybrid edge

Awesome stuff!!!

Can’t wait to try it out!

can you chat privately with a cloud llm—*without* sacrificing speed? excited to release minions secure chat: an open-source protocol for end-to-end encrypted llm chat with <1% latency overhead (even @ 30B+ params!). cloud providers can’t peek—messages decrypt only inside a

We secure all communications with a cloud-hosted LLM, running on an H100 in confidential mode. Latency overhead goes away once you cross the 10B model size. This is our first foray into applied cryptography -- help us refine our ideas.

pretty cool work!

Damn that’s⚡️ fast

Bravo! that's a lot of tools!

Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–Snorkel AI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D! ---

Happy Throughput Thursday! We’re excited to release Tokasaurus: an LLM inference engine designed from the ground up for high-throughput workloads with large and small models. (Joint work with Ayush Chakravarthy, Ryan Ehrlich, Sabri Eyuboglu, Bradley Brown, Joseph Shetaye,

This is a damn cool way to do long context hazyresearch

Hermann is awesome

🔥🔥🔥

Pleasure to chat with my teammate Vivek Natarajan to nature news, about our work Google DeepMind on AI co-scientist. "What’s it like to work with an AI team of virtual scientists?" 👇 nature.com/articles/d4158…