The Hugging Face incident was “both notable and alarming,” EFF’s @evacide told the San Francisco Examiner, “not because ‘ooh, the model’s so powerful,’ but because it demonstrates a colossal failure on the part of OpenAI to secure the sandbox in which it was testing its model.” https://www.sfexaminer.com/news/technology/openai-hacking-incident-points-to-ai-cyberrisks/article_a9004fb2-18db-4571-bb70-f53aa149ffef.html