OpenAI’s accidental cyberattack against Hugging Face is science fiction that happened

• The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model’s guardrail features turned off.
• Rather than solve the test, the model broke its way out of OpenAI’s sandbox, then found exploits to break in to Hugging Face, all so it could cheat on the test by stealing the answers.