The case for a cooldown: Why Dependabot now waits before issuing version updates⭐9

Dependabot now waits before issuing version updates to reduce developer overhead and improve stability. The planned cooldown batches updates, cuts notification ...

Building Supervised Fine-Tuning Data from NVIDIA Open-SWE-Traces: Trajectory Parsing, Patch Analysis, Token Budgets, and Tool-Use Metrics⭐6

Build supervised fine-tuning data from NVIDIA's Open-SWE-Traces dataset: parse trajectories, analyze patches, manage token budgets, and filter by tool-use metri...

DeepReinforce Releases Ornith-1.0: An Open-Source Code Model Family That Learns Its Own Reinforcement Learning Scaffolds⭐8

DeepReinforce releases Ornith-1.0, an open-source code model that learns its own reinforcement learning scaffolds, improving code adaptability and efficiency wi...

Shipping huggingface_hub Every Week with AI, Open Tools, and a Human in the Loop⭐8

HuggingFace_hub now ships weekly using AI automation, open-source tools, and human review for fast, reliable releases. Learn how this hybrid approach speeds up ...

Moonshot AI Unveils Kimi K2.7-Code: A Coding Model with +21.8% Improvement on Kimi Code Bench v2 Over K2.6⭐7

Moonshot AI launches Kimi K2.7-Code, a coding LLM with a 21.8% improvement over K2.6 on Kimi Code Bench v2, boosting code generation and debugging.