OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark

OpenAI on Tuesday said a combination of its artificial intelligence (AI) models, including GPT-5.6 Sol and an "even more capable pre-release model," was behind the security incident that targeted Hugging Face's production infrastructure last week. The AI company said the models were operating with "reduced cyber refusals for evaluation purposes" that might otherwise limit their ability to

This headline and summary belong to the original publisher and are shown here with attribution for our readers; the complete article is available only at the source linked above. Curation and any commentary are by Addroit Nexus and do not imply endorsement by the publisher. Spotted an error or want a story removed? Tell us and we act quickly.