LLMs for GPU kernel🌽generation have been getting Pop🍿ular since our preview last Dec; excited to announce 📢 our full paper 📃 for KernelBench!. Turns out KernelBench is quite challenging 🧠 — frontier models outperform the PyTorch Eager baseline <20% of the time. More 🧵👇

RT @aidangomez: Big news today: we’ve raised $500M to grow @cohere, and have added some incredible new leaders to our team!. We’re fortunat….

RT @oshaikh13: If you thought referencing past chats was cool, we built an MCP that lets Claude use *anything you see or do on your compute….

RT @khoomeik: tons of startups are selling RL envs to frontier labs rn. is there a Scale or Mercor to be built for RL envs?. one difference….

RT @MingYin_0312: I implemented GRPO and DPO from scratch in vanilla Pytorch to unravel every piece of training details. Hope it could be h….

RT @daniel_d_kang: The prevailing wisdom is that compute is the most important factor for frontier AI training. We think this is wrong: dat….

RT @robertnishihara: I don't think it's very widely known how big of a role @istoica05 and the research community at UC Berkeley have playe….

RT @bonniesjli: Genie 3 is here, the most advanced foundation world model. 🌎. In just a few months, we achieved real-time capabilities, lon….

RT @GoogleDeepMind: What if you could not only watch a generated video, but explore it too? 🌐. Genie 3 is our groundbreaking world model th….

RT @sama: gpt-oss is a big deal; it is a state-of-the-art open-weights reasoning model, with strong real-world performance comparable to o4….

RT @zhuohan123: I’ve been fortunate to lead the infra and inference work that brings gpt-oss to life. A year ago, I joined OpenAI after bui….

RT @Azaliamirh: Happy to share RoboMonkey, a framework for synthetic data generation + scaling test time compute for VLAs: . Turns out gene….

RT @mims: The AI infrastructure build-out is so gigantic that in the past 6 months, it contributed more to the growth of the U.S. economy t….

RT @aryaman2020: all i needed to read

RT @anneouyang: KernelBench v0.1 is out, featuring:.- A guideline on analyzing the validity of results and ruling out physically impossible….

RT @nickfrosst: 👁️👁️ . Cohere has a vision model now.

RT @SemiAnalysis_: When eager mode fallback quickly swoops after it hits a part of the graph that torch.compile can't compile.

RT @tilderesearch: ~4/8~ For the forward pass, we developed a specialized two-kernel implementation. The first fuses gather, projections, a….

RT @tilderesearch: Mixture‑of‑Experts (MoE) powers many frontier models like R1, K2, & Qwen3. ⚡️ To make frontier-scale MoE models accessib….

Turn old photos into videos and see friends and family come to life. Try Grok Imagine, free for a limited time.

RT @sid_srk: Announcing The Toronto School Of Foundation Modelling, a Toronto exclusive, in-person only school for learning to build Founda….

RT @marksaroufim: On Sep 6 in NYC, this won't be your typical hackathon where you do your own thing in a corner and then present at the of….