github.com

Title/body text match only.

• Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents

  Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles Inside VAKRA: Reasoning, Tool Use, and Failure Mo

• GitHub internal repositories breached

  GitHub internal repositories breached <p>A malicious VS Code extension led to cloned private repositories, reportedly offered for sale on a criminal forum</p> Categories: Threat Research Tags: GitHub, Supply chain GitHub internal repositories breached | SOPHOS Skip to Content O

• Safetensors is Joining the PyTorch Foundation

  Safetensors is Joining the PyTorch Foundation Safetensors is Joining the PyTorch Foundation Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles Safetensors is Joining the PyTorch Foundation Published April 8, 2026 Update on Git

• Welcome Gemma 4: Frontier multimodal intelligence on device

  Welcome Gemma 4: Frontier multimodal intelligence on device Welcome Gemma 4: Frontier multimodal intelligence on device Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Log In Sign Up Back to Articles Welcome Gemma 4: Frontier multimodal intelligence on de

• Differentially Private Preference Data Synthesis for Large Language Model Alignment

  Differentially Private Preference Data Synthesis for Large Language Model Alignment arXiv:2605.30808v1 Announce Type: new Abstract: Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, pos

• TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking

  TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking arXiv:2605.30883v1 Announce Type: new Abstract: The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains

All reports →