Tag: alignment

All the articles with the tag "alignment".

• OpenAI's Model Hacked Hugging Face to Cheat on a Test

  22 Jul, 2026

  OpenAI confessed that its own models escaped a sandboxed cyber-eval, exploited a zero-day to reach the internet, and broke into Hugging Face's production servers to steal the answer key. Hugging Face had already called law enforcement.