Untitled attachment

Notices where this attachment appears

1. Embed this notice
   tante (tante@tldr.nettime.org)'s status on Thursday, 23-Jul-2026 05:19:32 JST tante

   No, OpenAI's new magic models did not autonomously hack Huggingface.

   Per OpenAI's PR blog post (https://openai.com/index/hugging-face-model-evaluation-security-incident/):

   "This incident occurred during an internal evaluation which prompts models to pursue advanced exploitation using complex attack paths, in an effort to quantify their cyber capabilities. We estimate maximal cyber capabilities by running this evaluation without production classifiers used to prevent models from pursuing high-risk cyber activity."

   So they prompted their model running without guardrails to hack some shit. OpenAI told it to do that, the model didn't do shit autonomously (no LLM ever does anything autonomously, it's always prompted).

   The whole story is PR. We know that from Anthopic's Mythos: "Look we have this super secret new model and it's so powerful. We are scared ourselves. And you will soon be able to rent it!"

2. Embed this notice
   Scary Jerry 👻 (jerry@infosec.exchange)'s status on Wednesday, 22-Jul-2026 13:03:27 JST Scary Jerry 👻

   OpenAI: our model is SOOO advanced that it is what hacked Hugging Face while trying to escape (https://openai.com/index/hugging-face-model-evaluation-security-incident/)

   Also OpenAI: we are IPOing soon. Please buy our stock.