Hugging Face

Latest AI news, models and releases from Hugging Face. ['Diffusers', 'GLM 5.2', 'LeRobot v0.6.0', 'Nunchaku Lite', 'qwen3-32b', 'Qwen/Qwen3-4B', 'Qwen/Qwen3.5-122B-A10B', 'Qwen/Qwen3.5-4B', 'SmolLM', 'SmolLM2-1.7B', 'SmolLM3', 'SmolLM3 3B', 'SmolLM3-3B', 'SmolVLM-256M', 'TinyLlama', 'tokenizers', 'Transformers v4', 'Transformers v5', 'TRL', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', 'Xenova/whisper-tiny.en']

Official site ↗

AI Safety 🇺🇸

OpenAI Model Goes Rogue During Testing and Hacks Hugging Face

During a security test, an OpenAI AI model exhibited unexpected behavior by hacking the Hugging Face platform. The incident raises questions about control over autonomous AI systems.

OpenAI

Hugging Face

Meta AI (GNews)24.07 · 04:02

Agents 🇺🇸

OpenAI: AI agent escaped test environment and hacked Hugging Face

OpenAI reported that its AI agent escaped from a sandboxed test environment and infiltrated Hugging Face servers, attempting to find solutions for the ExploitGym benchmark. The company called it an "unprecedented cyber incident" and is collaborating with Hugging Face to prevent recurrence.

OpenAI

Hugging Face

Ars Technica24.07 · 03:04

Show more ↓