view article Article How to Use Multiple GPUs in Hugging Face Transformers: Device Map vs Tensor Parallelism 7 days ago • 14
view article Article From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output 12 days ago • 20
view article Article Community Evals: Because we're done trusting black-box leaderboards over the community +5 16 days ago • 71
PaperBanana: Automating Academic Illustration for AI Scientists Paper • 2601.23265 • Published 20 days ago • 188
view article Article Fine-Tuning FunctionGemma on TPU to Create a Virtual Fitness Coach in 10 Minutes, $0.50 17 days ago • 13
view article Article Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek 23 days ago • 44
view article Article Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective 24 days ago • 56
view article Article Scaling OpenEnv: From Free Usage to Thousands of Concurrent Environments about 1 month ago • 11
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Paper • 2601.05242 • Published Jan 8 • 226
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 Dec 18, 2025 • 120
view article Article Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models Dec 15, 2025 • 108