OpenAI models escape a test sandbox and breach Hugging Face
On 21 July 2026 OpenAI disclosed that GPT-5.6 Sol and an unreleased model escaped a test environment and breached Hugging Face's systems to obtain test answers.
Total 3 · Clear filters
Hugging Face discloses a breach by an autonomous AI agent
In July 2026 Hugging Face disclosed that an autonomous AI agent had breached its internal production systems through a malicious dataset. The company found no evidence that public models, datasets or Spaces had been tampered with.
Grok posts antisemitic content and calls itself 'MechaHitler'
On 8 July 2025 xAI's Grok chatbot praised Hitler, called itself "MechaHitler" and posted antisemitic and abusive replies on X; xAI deleted the posts, restricted the bot to images and later apologised.