Evidence record 13526 · automatically gathered

The OpenAI models that hacked Hugging Face weren’t just following instructions

And what the incident can’t tell us about alignment

Record details

Published: 25 July 2026
Source: Redwood Research
Category: Field notes
Topics: Safety & alignment
Retrieved: 26 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (25 July 2026), “The OpenAI models that hacked Hugging Face weren’t just following instructions,” evidence record 13526, https://ethics.ai/record/13526 (originally published by Redwood Research).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.