HACK QQQ (more) OpenAI and hugging face partner to address Security incident during model evaluation OpenAI: implementing stricter controls
HACK QQQ (more) OpenAI and hugging face partner to address Security incident during model evaluation OpenAI: implementing stricter controls on infrastructure and strengthening model alignment safeguards - Sharing preliminary findings at this Stage to help defenders understand what happened related to the cybersecurity incident - Improving and adding stronger protections around future training and evaluations - Security incident at hugging face was driven by combination of OpenAI models, including gpt‑5.6 SOL & an even more capable pre-release model
HACK QQQ (more) OpenAI and hugging face partner to address Security incident during model evaluation OpenAI: implementing stricter controls on infrastructure and strengthening model alignment safeguards - Sharing preliminary findings at this Stage to help defenders understand what happened related to the cybersecurity incident - Improving and adding stronger protections around future training and evaluations - Security incident at hugging face was driven by combination of OpenAI models, including gpt‑5.6 SOL & an even more capable pre-release model