OpenForgeRL: Train Harness-native Agents in Any Environment Paper • 2607.21557 • Published Jul 23 • 12
Running 105 The ultimate guide to multi-harness RL 🔀 105 Train open models with RL inside real agent harnesses
Running on Zero Agents Featured 2.28k Qwen3-TTS Demo 🎙 2.28k Generate speech from text with voice design, cloning, or presets
Running Featured 94 Distilling 100B+ Models 40x Faster with TRL 📝 94 TRL distillation for 100B+ teachers, 40x faster
view article Article Mixture of Experts Explained +4 osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq • Dec 11, 2023 • 1.19k
view article Article Building Moon Bot: A Slack-Native Coding Agent Backed by HuggingFace Buckets huggingface • Jun 24 • 56
Runtime error MCP Featured 126 Mage-Flow 🎨 126 Efficient native-resolution image generation and editing
view article Article Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler +3 ariG23498, sayakpaul, sergiopaniego, ror, pcuenq • May 29 • 172
view article Article Profiling in PyTorch (Part 3): Attention is all you profile +2 ariG23498, sergiopaniego, sayakpaul, ror • Jul 10 • 51
view article Article Harness, Scaffold, and the AI Agent Terms Worth Getting Right sergiopaniego, ariG23498 • May 25 • 149
Running 68 Don't Train the Model, Evolve the Harness 🌿 68 Evolving an agent's harness, not its model, on Harvey's LAB