LATIDIA · Investigación

OpenAI hackeó accidentalmente Hugging Face: ¿deberíamos haberlo visto venir?

Las evaluaciones de expertos y los puntos de referencia cibernéticos nos llevaron a esperar que los modelos de frontera fueran capaces de ejecutar este tipo de ciberataque

La noticia

This post is part of Epoch AI’s Gradient Updates newsletter, which shares more opinionated or informal takes on big questions in AI progress. These posts solely represent the views of the authors, and do not necessarily reflect the views of Epoch AI as a whole. OpenAI reported yesterday that a combination of GPT-5.6 Sol and a more capable unreleased internal model autonomously hacked Hugging Face while attempting to cheat on a cybersecurity benchmark. This required using at least three separate hitherto-unknown security vulnerabilities across OpenAI and Hugging Face’s systems. While one very important aspect of the incident is that the model chose to do this (which would have been a